starred/altstack-data
1
0
Fork 0
mirror of https://github.com/altstackHQ/altstack-data.git synced 2026-04-17 21:53:12 +02:00
Code Issues Packages Projects Releases Wiki Activity
Files
81c306138f911c30c62765d67c5cebed3a1013ac
altstack-data/data/tools.json
aa_humaaan 81c306138f feat: add tymeslot (#6)
2026-03-06 23:46:59 +05:30

18302 lines
468 KiB
JSON
Raw Blame History

[
{
"slug": "firebase",
"name": "Firebase",
"category": "Backend as a Service",
"is_open_source": false,
"pricing_model": "Paid/Freemium",
"website": "https://firebase.google.com",
"description": "Google's app development platform.",
"alternatives": [
"supabase",
"appwrite",
"pocketbase"
],
"tags": [
"Cloud",
"Database",
"Auth"
],
"logo_url": "/logos/firebase.svg",
"avg_monthly_cost": 25,
"pros": [
"Seamless Google ecosystem integration",
"Generous free tier (Spark plan)",
"Real-time database out of the box",
"Excellent mobile SDK support",
"Cloud Functions for serverless logic"
],
"cons": [
"Vendor lock-in to Google",
"Pricing can spike unpredictably at scale",
"Limited query capabilities vs SQL"
]
},
{
"slug": "supabase",
"name": "Supabase",
"category": "Backend as a Service",
"is_open_source": true,
"github_repo": "supabase/supabase",
"stars": 97401,
"website": "https://supabase.com",
"description": "The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.",
"pros": [
"Postgres under the hood",
"No vendor lock-in"
],
"cons": [
"Self-hosting can be complex"
],
"last_commit": "2026-02-09T16:09:10Z",
"language": "TypeScript",
"license": "Apache License 2.0",
"tags": [
"Database",
"Realtime",
"Postgres",
"AI"
],
"logo_url": "/logos/supabase.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/supabase"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "appwrite",
"name": "Appwrite",
"category": "Backend as a Service",
"is_open_source": true,
"github_repo": "appwrite/appwrite",
"stars": 54727,
"website": "https://appwrite.io",
"description": "Appwrite\u00ae - complete cloud infrastructure for your web, mobile and AI apps. Including Auth, Databases, Storage, Functions, Messaging, Hosting, Realtime and more",
"pros": [
"Self-hosted with a single Docker command",
"Modular architecture \u2014 use only what you need"
],
"cons": [
"Smaller ecosystem than Firebase or Supabase",
"Limited built-in analytics and reporting"
],
"last_commit": "2026-02-09T16:12:32Z",
"language": "TypeScript",
"license": "BSD 3-Clause \"New\" or \"Revised\" License",
"tags": [
"Database",
"Auth",
"Self-Hosted"
],
"logo_url": "/logos/appwrite.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/appwrite"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "pocketbase",
"name": "PocketBase",
"category": "Backend as a Service",
"is_open_source": true,
"github_repo": "pocketbase/pocketbase",
"website": "https://pocketbase.io",
"description": "Open Source realtime backend in 1 file",
"pros": [
"Ships as a single binary \u2014 no dependencies",
"Deploy anywhere in seconds with zero config",
"Embedded SQLite with realtime subscriptions"
],
"cons": [
"SQLite only (for now)"
],
"stars": 55980,
"last_commit": "2026-02-01T08:09:48Z",
"language": "Go",
"license": "MIT License",
"logo_url": "/logos/pocketbase.svg",
"deployment": {
"image": "pocketbase/pocketbase:latest",
"port": 8090,
"volumes": [
"./pb_data:/pb/pb_data"
],
"command": "serve --http=0.0.0.0:8090",
"type": "docker-compose",
"local_path": "./.docker-deploy/pocketbase"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "salesforce",
"name": "Salesforce",
"category": "CRM",
"is_open_source": false,
"pricing_model": "Paid",
"avg_monthly_cost": 25,
"website": "https://salesforce.com",
"description": "The world's #1 CRM.",
"alternatives": [
"odoo",
"erpnext"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=salesforce.com",
"pros": [
"Industry-leading CRM platform",
"Massive app marketplace (AppExchange)",
"Highly customizable workflows",
"Enterprise-grade security and compliance"
],
"cons": [
"Expensive per-seat licensing",
"Steep learning curve",
"Heavy and complex for small teams"
]
},
{
"slug": "slack",
"name": "Slack",
"category": "Communication",
"is_open_source": false,
"pricing_model": "Paid/Freemium",
"website": "https://slack.com",
"description": "Team communication platform.",
"alternatives": [
"mattermost",
"rocketchat"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=slack.com",
"avg_monthly_cost": 12,
"pros": [
"Best-in-class team communication UX",
"Huge integration ecosystem (2,000+ apps)",
"Powerful search across conversations",
"Thread-based discussions reduce noise"
],
"cons": [
"Expensive at scale ($8.75+/user/mo)",
"Can become a constant distraction",
"Message history limits on free plan"
]
},
{
"slug": "mattermost",
"name": "Mattermost",
"category": "Communication",
"is_open_source": true,
"github_repo": "mattermost/mattermost",
"website": "https://mattermost.com",
"description": "Mattermost is an open source platform for secure collaboration across the entire software development lifecycle..",
"pros": [
"Enterprise-grade security with SOC2 and HIPAA compliance",
"Granular access control and audit logging",
"Slack-compatible webhook and bot ecosystem"
],
"cons": [
"Self-hosting maintenance"
],
"stars": 35213,
"last_commit": "2026-02-09T16:03:54Z",
"language": "TypeScript",
"license": "Other",
"logo_url": "/logos/mattermost.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/mattermost"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "rocketchat",
"name": "Rocket.Chat",
"category": "Communication",
"is_open_source": true,
"github_repo": "RocketChat/Rocket.Chat",
"website": "https://rocket.chat",
"description": "The Secure CommsOS\u2122 for mission-critical operations",
"pros": [
"Unified inbox with omnichannel support for live chat, email, and social",
"Highly customizable with white-labeling options",
"End-to-end encrypted messaging available"
],
"cons": [
"Resource intensive"
],
"stars": 44546,
"last_commit": "2026-02-09T16:20:40Z",
"language": "TypeScript",
"license": "Other",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=rocket.chat",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/rocketchat"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "jira",
"name": "Jira",
"category": "Project Management",
"is_open_source": false,
"pricing_model": "Paid",
"avg_monthly_cost": 15,
"website": "https://www.atlassian.com/software/jira",
"description": "Issue tracking and project management tool.",
"alternatives": [
"plane",
"taiga"
],
"logo_url": "/logos/jira.svg",
"pros": [
"Industry standard for project management",
"Deep Agile/Scrum/Kanban support",
"Powerful custom workflows and automation",
"Extensive integration ecosystem"
],
"cons": [
"Notoriously complex UI",
"Slow performance with large projects",
"Expensive for growing teams"
]
},
{
"slug": "plane",
"name": "Plane",
"category": "Project Management",
"is_open_source": true,
"github_repo": "makeplane/plane",
"website": "https://plane.so",
"description": "\ud83d\udd25\ud83d\udd25\ud83d\udd25 Open-source Jira, Linear, Monday, and ClickUp alternative. Plane is a modern project management platform to manage tasks, sprints, docs, and triage.",
"pros": [
"Clean, modern interface inspired by Linear",
"Blazing fast \u2014 sub-100ms interactions",
"Built-in cycles, modules, and views"
],
"cons": [
"Still relatively new"
],
"stars": 45490,
"last_commit": "2026-02-09T13:56:47Z",
"language": "TypeScript",
"license": "GNU Affero General Public License v3.0",
"logo_url": "/logos/plane.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/plane"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "taiga",
"name": "Taiga",
"category": "Project Management",
"is_open_source": true,
"github_repo": "taigaio/taiga-back",
"website": "https://taiga.io",
"description": null,
"pros": [
"Beautiful, kanban and scrum boards with drag-and-drop",
"Full Agile toolkit: epics, sprints, user stories",
"Built-in wiki and project documentation"
],
"cons": [
"Complex setup"
],
"stars": 807,
"last_commit": "2026-01-09T07:28:59Z",
"language": "Python",
"license": "Mozilla Public License 2.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=taiga.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/taiga"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "zoom",
"name": "Zoom",
"category": "Communication",
"is_open_source": false,
"pricing_model": "Paid/Freemium",
"avg_monthly_cost": 15,
"website": "https://zoom.us",
"description": "Video conferencing platform, cloud phone, webinars, and chat.",
"alternatives": [
"jitsi-meet"
],
"logo_url": "/logos/zoom.svg",
"pros": [
"Reliable video quality even on poor connections",
"Easy to join without creating an account",
"Breakout rooms and webinar support for large events",
"Cross-platform with desktop, mobile, and web apps"
],
"cons": [
"Free plan limited to 40-minute meetings",
"Privacy concerns and past security issues",
"Zoom fatigue is real"
]
},
{
"slug": "jitsi-meet",
"name": "Jitsi Meet",
"category": "Communication",
"is_open_source": true,
"github_repo": "jitsi/jitsi-meet",
"website": "https://jitsi.org",
"description": "Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.",
"pros": [
"Join calls without creating an account",
"End-to-end encrypted video conferencing",
"Scales to hundreds of participants with Jitsi Videobridge"
],
"cons": [
"Performance on large calls"
],
"stars": 28562,
"last_commit": "2026-02-09T12:49:10Z",
"language": "TypeScript",
"license": "Apache License 2.0",
"logo_url": "/logos/jitsi-meet.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/jitsi-meet"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "photoshop",
"name": "Adobe Photoshop",
"category": "Design",
"is_open_source": false,
"pricing_model": "Paid (Monthly)",
"avg_monthly_cost": 60,
"website": "https://www.adobe.com/products/photoshop.html",
"description": "Industry standard image editing software.",
"alternatives": [
"gimp",
"krita"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=www.adobe.com",
"pros": [
"Industry gold standard for image editing",
"Unmatched feature depth and precision",
"Huge plugin and template ecosystem",
"AI-powered generative fill and selection"
],
"cons": [
"Subscription-only pricing ($22.99/mo)",
"Steep learning curve for beginners",
"Resource-heavy \u2014 needs powerful hardware"
]
},
{
"slug": "gimp",
"name": "GIMP",
"category": "Design",
"is_open_source": true,
"github_repo": "GNOME/gimp",
"website": "https://www.gimp.org",
"description": "Read-only mirror of https://gitlab.gnome.org/GNOME/gimp",
"pros": [
"Professional-grade photo editing tools rivaling Photoshop",
"Extensible with Python and Script-Fu plugins",
"Cross-platform with native support for PSD, TIFF, and RAW"
],
"cons": [
"Steep learning curve",
"Dated UI"
],
"stars": 5960,
"last_commit": "2026-02-09T16:20:25Z",
"language": "C",
"license": "Other",
"logo_url": "/logos/gimp.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "krita",
"name": "Krita",
"category": "Design",
"is_open_source": true,
"github_repo": "KDE/krita",
"website": "https://krita.org",
"description": "Krita is a free and open source cross-platform application that offers an end-to-end solution for creating digital art files from scratch built on the KDE and Qt frameworks.",
"pros": [
"Modern brush engine with 100+ built-in presets",
"HDR painting and animation timeline support",
"Optimized for drawing tablets with pressure sensitivity"
],
"cons": [
"Less focused on photo manipulation"
],
"stars": 9333,
"last_commit": "2026-02-09T13:47:56Z",
"language": "C++",
"license": "GNU General Public License v3.0",
"logo_url": "/logos/krita.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "figma",
"name": "Figma",
"category": "Design",
"is_open_source": false,
"pricing_model": "Freemium/Paid",
"website": "https://www.figma.com",
"description": "Collaborative interface design tool.",
"alternatives": [
"penpot"
],
"logo_url": "/logos/figma.svg",
"avg_monthly_cost": 15,
"pros": [
"Real-time multiplayer collaboration",
"Runs entirely in the browser",
"Excellent component and design system support",
"Free tier is generous for individuals"
],
"cons": [
"Owned by Adobe (future pricing concerns)",
"Offline support is limited",
"Performance with very large files can lag"
]
},
{
"slug": "penpot",
"name": "Penpot",
"category": "Design",
"is_open_source": true,
"github_repo": "penpot/penpot",
"website": "https://penpot.app",
"description": "Penpot: The open-source design tool for design and code collaboration",
"pros": [
"Runs entirely in the browser \u2014 no desktop app needed",
"SVG-native design \u2014 exports are pixel-perfect at any scale",
"Real-time multiplayer collaboration"
],
"cons": [
"Newer ecosystem"
],
"stars": 44155,
"last_commit": "2026-02-09T15:47:35Z",
"language": "Clojure",
"license": "Mozilla Public License 2.0",
"logo_url": "/logos/penpot.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/penpot"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "notion",
"name": "Notion",
"category": "Productivity",
"is_open_source": false,
"pricing_model": "Freemium/Paid",
"website": "https://www.notion.so",
"description": "All-in-one workspace.",
"alternatives": [
"appflowy",
"affine"
],
"logo_url": "/logos/notion.svg",
"avg_monthly_cost": 10,
"pros": [
"All-in-one workspace (docs, wikis, databases)",
"Beautiful and intuitive interface",
"Powerful database views and relations",
"Great template gallery"
],
"cons": [
"Can be slow with large workspaces",
"Offline mode is unreliable",
"No true end-to-end encryption"
]
},
{
"slug": "appflowy",
"name": "AppFlowy",
"category": "Productivity",
"is_open_source": true,
"github_repo": "AppFlowy-IO/AppFlowy",
"website": "https://www.appflowy.io",
"description": "Bring projects, wikis, and teams together with AI. AppFlowy is the AI collaborative workspace where you achieve more without losing control of your data. The leading open source Notion alternative.",
"pros": [
"Local-first architecture \u2014 your data never leaves your machine",
"Privacy-focused alternative to Notion",
"Built in Rust for native desktop performance"
],
"cons": [
"No web version (yet)"
],
"stars": 68006,
"last_commit": "2026-01-28T09:20:38Z",
"language": "Dart",
"license": "GNU Affero General Public License v3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=www.appflowy.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/appflowy"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "affine",
"name": "AFFiNE",
"category": "Productivity",
"is_open_source": true,
"github_repo": "toeverything/AFFiNE",
"website": "https://affine.pro",
"description": "There can be more than Notion and Miro. AFFiNE(pronounced [\u0259\u2018fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use. ",
"pros": [
"Modern block editor with Notion-like feel",
"Spatial canvas for whiteboarding and visual thinking",
"Hybrid local-first and cloud sync architecture"
],
"cons": [
"Still in beta"
],
"stars": 62693,
"last_commit": "2026-02-09T11:16:50Z",
"language": "TypeScript",
"license": "Other",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=affine.pro",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/affine"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "google-analytics",
"name": "Google Analytics",
"category": "Analytics",
"is_open_source": false,
"pricing_model": "Free/Paid",
"website": "https://analytics.google.com",
"description": "Web analytics service.",
"alternatives": [
"plausible",
"posthog",
"matomo"
],
"logo_url": "/logos/google-analytics.svg",
"avg_monthly_cost": 150,
"pros": [
"Industry-standard reporting with Google Ads and Search Console integration",
"Advanced audience segmentation and cohort analysis",
"Free tier handles up to 10M hits per month"
],
"cons": [
"Privacy concerns \u2014 data goes to Google",
"GA4 migration frustrated many users",
"Blocked by most ad blockers",
"Complex for beginners"
]
},
{
"slug": "plausible",
"name": "Plausible",
"category": "Analytics",
"is_open_source": true,
"github_repo": "plausible/analytics",
"website": "https://plausible.io",
"description": "Simple, open source, lightweight and privacy-friendly web analytics alternative to Google Analytics.",
"pros": [
"Fully GDPR compliant with no cookies required",
"Lightweight script under 1KB \u2014 zero impact on page speed",
"Clean dashboard that shows what matters, nothing more"
],
"cons": [
"Limited advanced features"
],
"stars": 24198,
"last_commit": "2026-02-09T16:20:52Z",
"language": "Elixir",
"license": "GNU Affero General Public License v3.0",
"tags": [
"Analytics",
"Privacy",
"GDPR"
],
"logo_url": "/logos/plausible.svg",
"deployment": {
"image": "plausible/analytics:latest",
"port": 8000,
"env": [
{
"key": "BASE_URL",
"value": "http://localhost:8000"
},
{
"key": "SECRET_KEY_BASE",
"value": "REPLACE_WITH_RANDOM_STRING"
}
],
"volumes": [
"./plausible_db:/var/lib/clickhouse",
"./plausible_events:/var/lib/postgresql/data"
],
"type": "docker-compose",
"local_path": "./.docker-deploy/plausible"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "posthog",
"name": "PostHog",
"category": "Analytics",
"is_open_source": true,
"github_repo": "PostHog/posthog",
"website": "https://posthog.com",
"description": "\ud83e\udd94 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack.",
"pros": [
"Session recording with heatmaps and click tracking",
"Built-in feature flags, A/B testing, and surveys",
"Warehouse-native \u2014 query your data with SQL"
],
"cons": [
"Complex to self-host"
],
"stars": 31181,
"last_commit": "2026-02-09T16:25:10Z",
"language": "Python",
"license": "Other",
"logo_url": "/logos/posthog.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/posthog"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "matomo",
"name": "Matomo",
"category": "Analytics",
"is_open_source": true,
"github_repo": "matomo-org/matomo",
"website": "https://matomo.org",
"description": "Empowering People Ethically \ud83d\ude80 \u2014 Matomo is hiring! Join us \u2192 https://matomo.org/jobs Matomo is the leading open-source alternative to Google Analytics, giving you complete control and built-in privacy. Easily collect, visualise, and analyse data from websites & apps. Star us on GitHub \u2b50\ufe0f \u2013 Pull Requests welcome! ",
"pros": [
"Feature-rich analytics rivaling Google Analytics",
"GDPR and CCPA compliant out of the box",
"Heatmaps, session recordings, and funnel analysis included"
],
"cons": [
"UI feels dated"
],
"stars": 21270,
"last_commit": "2026-02-09T15:36:30Z",
"language": "PHP",
"license": "GNU General Public License v3.0",
"logo_url": "/logos/matomo.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/matomo"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "1password",
"name": "1Password",
"category": "Security",
"is_open_source": false,
"pricing_model": "Paid",
"website": "https://1password.com",
"description": "Password manager.",
"alternatives": [
"bitwarden",
"keepassxc"
],
"logo_url": "/logos/1password.svg",
"avg_monthly_cost": 8,
"pros": [
"Excellent cross-platform support",
"Travel Mode hides sensitive vaults",
"Watchtower alerts for compromised passwords",
"Family and team sharing built in"
],
"cons": [
"No free tier ($2.99/mo minimum)",
"Cloud-only \u2014 no self-hosting option",
"Subscription model with no lifetime option"
]
},
{
"slug": "bitwarden",
"name": "Bitwarden",
"category": "Security",
"is_open_source": true,
"github_repo": "bitwarden/server",
"website": "https://bitwarden.com",
"description": "Bitwarden infrastructure/backend (API, database, Docker, etc).",
"pros": [
"Independently audited security with full transparency reports",
"Cross-platform apps for every OS, browser, and device",
"Organization vaults with fine-grained sharing controls"
],
"cons": [
"UI is functional but basic"
],
"stars": 18027,
"last_commit": "2026-02-09T15:52:04Z",
"language": "C#",
"license": "Other",
"logo_url": "/logos/bitwarden.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/bitwarden"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "keepassxc",
"name": "KeePassXC",
"category": "Security",
"is_open_source": true,
"github_repo": "keepassxreboot/keepassxc",
"website": "https://keepassxc.org",
"description": "KeePassXC is a cross-platform community-driven port of the Windows application \u201cKeePass Password Safe\u201d.",
"pros": [
"Fully offline \u2014 database stored locally with AES-256 encryption",
"No cloud dependency \u2014 you control the sync method",
"Browser integration via KeePassXC-Browser extension"
],
"cons": [
"No automatic sync (requires Dropbox/Syncthing)"
],
"stars": 25810,
"last_commit": "2026-01-18T15:46:48Z",
"language": "C++",
"license": "Other",
"logo_url": "/logos/keepassxc.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/keepassxc"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "heroku",
"name": "Heroku",
"category": "DevOps",
"is_open_source": false,
"pricing_model": "Paid",
"avg_monthly_cost": 8,
"website": "https://heroku.com",
"description": "Platform as a service.",
"alternatives": [
"coolify",
"dokku"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=heroku.com",
"pros": [
"Dead-simple deployment (git push)",
"Great for prototypes and MVPs",
"Managed Postgres included",
"Add-ons marketplace for common services"
],
"cons": [
"Eliminated free tier in 2022",
"Expensive at scale vs VPS",
"Limited container customization",
"Owned by Salesforce (less innovation)"
]
},
{
"slug": "coolify",
"name": "Coolify",
"category": "DevOps",
"is_open_source": true,
"github_repo": "coollabsio/coolify",
"website": "https://coolify.io",
"description": "An open-source, self-hostable PaaS alternative to Vercel, Heroku & Netlify that lets you easily deploy static sites, databases, full-stack applications and 280+ one-click services on your own servers.",
"pros": [
"Polished, beautiful dashboard that rivals Vercel and Netlify",
"Deploy anything \u2014 Docker, static sites, databases, services",
"Automatic SSL, backups, and monitoring included"
],
"cons": [
"One-man project (mostly)"
],
"stars": 50421,
"last_commit": "2026-02-09T16:01:12Z",
"language": "PHP",
"license": "Apache License 2.0",
"tags": [
"DevOps",
"PaaS",
"Self-Hosted"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=coolify.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/coolify"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "sap",
"name": "SAP S/4HANA",
"category": "ERP",
"is_open_source": false,
"pricing_model": "Paid (Enterprise)",
"avg_monthly_cost": 100,
"website": "https://www.sap.com",
"description": "The world leader in enterprise resource planning software.",
"alternatives": [
"odoo",
"erpnext"
],
"logo_url": "/logos/sap.svg",
"pros": [
"Enterprise ERP market leader",
"Handles massive organizational complexity",
"Deep industry-specific solutions",
"Strong compliance and audit trails"
],
"cons": [
"Extremely expensive to implement",
"Implementation takes months to years",
"Requires specialized consultants",
"Overkill for SMBs"
]
},
{
"slug": "odoo",
"name": "Odoo",
"category": "ERP",
"is_open_source": true,
"github_repo": "odoo/odoo",
"stars": 48919,
"website": "https://www.odoo.com",
"description": "A suite of open source business apps: CRM, eCommerce, accounting, manufacturing, warehouse, and more.",
"pros": [
"All-in-one suite covering CRM, HR, inventory, and accounting",
"Modular app marketplace with 30,000+ extensions",
"Dual licensing \u2014 Community (free) and Enterprise"
],
"cons": [
"Can be complex to customize",
"Enterprise features are paid"
],
"last_commit": "2026-02-09T16:18:46Z",
"language": "Python",
"license": "LGPL-3.0",
"logo_url": "/logos/odoo.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/odoo"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "erpnext",
"name": "ERPNext",
"category": "ERP",
"is_open_source": true,
"github_repo": "frappe/erpnext",
"website": "https://erpnext.com",
"description": "A free and open-source integrated Enterprise Resource Planning (ERP) software.",
"pros": [
"Fully open source",
"No licensing fees"
],
"cons": [
"Steep learning curve"
],
"stars": 31635,
"last_commit": "2026-02-09T15:52:29Z",
"language": "Python",
"license": "GNU General Public License v3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=erpnext.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/erpnext"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "autocad",
"name": "AutoCAD",
"category": "CAD",
"is_open_source": false,
"pricing_model": "Paid (Subscription)",
"website": "https://www.autodesk.com/products/autocad",
"description": "Professional computer-aided design (CAD) and drafting software.",
"alternatives": [
"librecad",
"freecad"
],
"logo_url": "/logos/autocad.svg",
"avg_monthly_cost": 75,
"pros": [
"Industry standard for CAD/engineering",
"Precise 2D and 3D modeling",
"Extensive library of tools and templates",
"Strong file format compatibility"
],
"cons": [
"Expensive subscription ($1,975/yr)",
"Steep learning curve",
"Resource-intensive \u2014 needs workstation hardware"
]
},
{
"slug": "librecad",
"name": "LibreCAD",
"category": "CAD",
"is_open_source": true,
"github_repo": "LibreCAD/LibreCAD",
"stars": 6500,
"website": "https://librecad.org",
"description": "A mature, feature-rich 2D CAD application with a loyal user community.",
"pros": [
"Purpose-built lightweight 2D CAD application",
"Native DXF support for industry-standard file exchange",
"Cross-platform with minimal system requirements"
],
"cons": [
"2D only"
],
"last_commit": "2026-02-05T10:00:00Z",
"language": "C++",
"license": "GPLv2",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=librecad.org",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "freecad",
"name": "FreeCAD",
"category": "CAD",
"is_open_source": true,
"github_repo": "FreeCAD/FreeCAD",
"stars": 21000,
"website": "https://www.freecad.org",
"description": "A general-purpose parametric 3D CAD modeler and a BIM software application.",
"pros": [
"Full parametric 3D modeling with constraint-based sketcher",
"Extensible 3D capabilities for mechanical engineering, architecture, and BIM",
"Python scripting and macro system for automation"
],
"cons": [
"UI learning curve"
],
"last_commit": "2026-02-08T14:00:00Z",
"language": "C++",
"license": "LGPLv2+",
"logo_url": "/logos/freecad.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "zapier",
"name": "Zapier",
"category": "Automation",
"is_open_source": false,
"pricing_model": "Paid (Task-based)",
"website": "https://zapier.com",
"description": "The pioneer in workflow automation for everyone.",
"alternatives": [
"n8n",
"activepieces"
],
"logo_url": "/logos/zapier.svg",
"avg_monthly_cost": 20,
"pros": [
"Connect 6,000+ apps without code",
"Easy visual workflow builder",
"Reliable trigger-based automation",
"Good for non-technical users"
],
"cons": [
"Gets expensive fast (per-task pricing)",
"Limited logic and branching on lower tiers",
"5-minute polling delay on some triggers"
]
},
{
"slug": "n8n",
"name": "n8n",
"category": "Automation",
"is_open_source": true,
"github_repo": "n8n-io/n8n",
"stars": 49000,
"website": "https://n8n.io",
"description": "Fair-code workflow automation tool. Easily automate tasks across different services.",
"pros": [
"Self-hosted workflow automation with 400+ integrations",
"Visual node-based editor for complex multi-step workflows",
"JavaScript/Python code nodes for custom logic"
],
"cons": [
"Requires hosting knowledge"
],
"last_commit": "2026-02-09T15:00:00Z",
"language": "TypeScript",
"license": "Sustainable Use License",
"logo_url": "/logos/n8n.svg",
"deployment": {
"image": "n8nio/n8n",
"port": 5678,
"env": [
{
"key": "N8N_BASIC_AUTH_ACTIVE",
"value": "true"
},
{
"key": "N8N_BASIC_AUTH_USER",
"value": "admin"
},
{
"key": "N8N_BASIC_AUTH_PASSWORD",
"value": "password"
}
],
"volumes": [
"./n8n_data:/home/node/.n8n"
],
"type": "docker-compose",
"local_path": "./.docker-deploy/n8n"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "activepieces",
"name": "Activepieces",
"category": "Automation",
"is_open_source": true,
"github_repo": "activepieces/activepieces",
"stars": 11000,
"website": "https://www.activepieces.com",
"description": "Open source alternative to Zapier. Automate your work with 200+ apps.",
"pros": [
"Beginner-friendly UI with a low learning curve",
"Open-source and self-hostable with Docker",
"Growing library of community-built connectors"
],
"cons": [
"Smaller connector library than Zapier"
],
"last_commit": "2026-02-09T16:00:00Z",
"language": "TypeScript",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=activepieces.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/activepieces"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "tableau",
"name": "Tableau",
"category": "Analytics",
"is_open_source": false,
"pricing_model": "Paid (Seat-based)",
"avg_monthly_cost": 70,
"website": "https://www.tableau.com",
"description": "Powerful data visualization and business intelligence platform.",
"alternatives": [
"metabase",
"superset"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=tableau.com",
"pros": [
"Best-in-class data visualization",
"Drag-and-drop dashboard creation",
"Handles massive datasets well",
"Strong community and learning resources"
],
"cons": [
"Expensive licensing ($70+/user/mo)",
"Requires a data warehouse setup",
"Desktop app feels dated"
]
},
{
"slug": "metabase",
"name": "Metabase",
"category": "Analytics",
"is_open_source": true,
"github_repo": "metabase/metabase",
"stars": 38000,
"website": "https://www.metabase.com",
"description": "The simplest, fastest way to get business intelligence and analytics throughout your company.",
"pros": [
"Extremely user friendly",
"Easy query builder"
],
"cons": [
"Advanced visualizations can be limited"
],
"last_commit": "2026-02-09T14:30:00Z",
"language": "Clojure",
"license": "AGPLv3",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=metabase.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/metabase"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "superset",
"name": "Apache Superset",
"category": "Analytics",
"is_open_source": true,
"github_repo": "apache/superset",
"stars": 59000,
"website": "https://superset.apache.org",
"description": "Enterprise-ready business intelligence web application.",
"pros": [
"Scaling to petabytes",
"Huge variety of charts"
],
"cons": [
"Complex configuration"
],
"last_commit": "2026-02-09T12:00:00Z",
"language": "Python",
"license": "Apache 2.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=superset.apache.org",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/superset"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "auth0",
"name": "Auth0",
"category": "Security",
"is_open_source": false,
"pricing_model": "Paid (MAU-based)",
"website": "https://auth0.com",
"description": "The leading authentication and authorization platform.",
"alternatives": [
"keycloak",
"authentik"
],
"logo_url": "/logos/auth0.svg",
"avg_monthly_cost": 23,
"pros": [
"Feature-rich authentication platform",
"Social login, MFA, and SSO out of the box",
"Extensive SDK support across languages",
"Rules and hooks for custom auth logic"
],
"cons": [
"Pricing jumps sharply after free tier",
"Can be complex to configure properly",
"Owned by Okta \u2014 consolidation concerns"
]
},
{
"slug": "keycloak",
"name": "Keycloak",
"category": "Security",
"is_open_source": true,
"github_repo": "keycloak/keycloak",
"stars": 23000,
"website": "https://www.keycloak.org",
"description": "Open source identity and access management for modern applications and services.",
"pros": [
"Enterprise-standard identity provider supporting SAML and OIDC",
"Federated identity with social login and LDAP integration",
"Battle-tested by Red Hat in production environments"
],
"cons": [
"UI can be clunky",
"Heavy resource usage"
],
"last_commit": "2026-02-09T16:30:00Z",
"language": "Java",
"license": "Apache 2.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=keycloak.org",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/keycloak"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "okta",
"name": "Okta",
"category": "Security",
"is_open_source": false,
"pricing_model": "Paid (User-based)",
"website": "https://okta.com",
"description": "The World's Identity Company, providing enterprise-grade IAM.",
"alternatives": [
"authentik",
"keycloak"
],
"logo_url": "/logos/okta.svg",
"avg_monthly_cost": 6,
"pros": [
"Enterprise SSO and identity management leader",
"Strong security and compliance certifications",
"Universal directory for user management",
"Extensive pre-built integrations"
],
"cons": [
"Very expensive for small teams",
"Admin interface has a learning curve",
"Overkill for simple auth needs"
]
},
{
"slug": "authentik",
"name": "Authentik",
"category": "Security",
"is_open_source": true,
"github_repo": "goauthentik/authentik",
"stars": 15000,
"website": "https://goauthentik.io",
"description": "The overall-best open-source identity provider, focused on flexibility and versatility.",
"pros": [
"Modern, intuitive admin interface with drag-and-drop flows",
"Easy customization of login pages and branding",
"Supports SAML, OAuth2, LDAP proxy, and SCIM"
],
"cons": [
"Smaller community than Keycloak"
],
"last_commit": "2026-02-09T17:00:00Z",
"language": "Python",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=goauthentik.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/authentik"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "s3",
"name": "Amazon S3",
"category": "Cloud Infrastructure",
"is_open_source": false,
"pricing_model": "Paid (Usage-based)",
"website": "https://aws.amazon.com/s3",
"description": "Object storage built to retrieve any amount of data from anywhere.",
"alternatives": [
"garage",
"seaweedfs",
"ceph",
"rustfs"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=aws.amazon.com",
"avg_monthly_cost": 23,
"pros": [
"99.999999999% durability (11 nines)",
"Scales to virtually unlimited storage",
"Pay only for what you use",
"Industry standard \u2014 everything integrates with it"
],
"cons": [
"Egress costs can surprise you",
"Complex IAM/bucket policy configuration",
"Vendor lock-in to AWS ecosystem"
]
},
{
"slug": "garage",
"name": "Garage",
"category": "Cloud Infrastructure",
"is_open_source": true,
"github_repo": "deuxfleurs-org/garage",
"stars": 3500,
"website": "https://garagehq.deuxfleurs.fr/",
"description": "An open-source distributed object storage service tailored for self-hosting.",
"pros": [
"True open-source (AGPLv3)",
"Lightweight and runs anywhere",
"Built-in replication and cluster management"
],
"cons": [
"Lacks some enterprise features of MinIO"
],
"last_commit": "2024-03-01T00:00:00Z",
"language": "Rust",
"license": "AGPLv3",
"logo_url": "/logos/garage.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/garage"
}
},
{
"slug": "zendesk",
"name": "Zendesk",
"category": "Support",
"is_open_source": false,
"pricing_model": "Paid (Agent-based)",
"avg_monthly_cost": 19,
"website": "https://www.zendesk.com",
"description": "The leader in customer service and engagement software.",
"alternatives": [
"zammad"
],
"logo_url": "/logos/zendesk.svg",
"pros": [
"Comprehensive customer support platform",
"Omnichannel support (email, chat, phone)",
"Powerful ticket management and routing",
"Large marketplace of integrations"
],
"cons": [
"Expensive per-agent pricing",
"UI can feel bloated and slow",
"Basic plans lack important features"
]
},
{
"slug": "zammad",
"name": "Zammad",
"category": "Support",
"is_open_source": true,
"github_repo": "zammad/zammad",
"stars": 5000,
"website": "https://zammad.org",
"description": "A web-based, open source helpdesk/customer support system with many features.",
"pros": [
"Omnichannel helpdesk with email, phone, chat, and social media",
"Full-text search with Elasticsearch integration",
"Customizable ticket workflows and SLA management"
],
"cons": [
"Ruby hosting can be tricky"
],
"last_commit": "2026-02-09T11:00:00Z",
"language": "Ruby",
"license": "AGPLv3",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=zammad.org",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/zammad"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "workday",
"name": "Workday",
"category": "HR",
"is_open_source": false,
"pricing_model": "Paid (Enterprise)",
"avg_monthly_cost": 45,
"website": "https://www.workday.com",
"description": "Enterprise management cloud for finance and human resources.",
"alternatives": [
"orangehrm"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=workday.com",
"pros": [
"Leading cloud HR and finance platform",
"Strong workforce analytics",
"Regular feature updates included",
"Built for enterprise compliance"
],
"cons": [
"Extremely expensive to implement",
"Long implementation timelines",
"Complex for smaller organizations"
]
},
{
"slug": "orangehrm",
"name": "OrangeHRM",
"category": "HR",
"is_open_source": true,
"github_repo": "orangehrm/orangehrm",
"stars": 1200,
"website": "https://www.orangehrm.com",
"description": "The world's most popular open source human resource management software.",
"pros": [
"Comprehensive HR suite covering recruitment, leave, and performance",
"Highly customizable with module-based architecture",
"Employee self-service portal for time-off and expenses"
],
"cons": [
"UI feels a bit dated",
"Enterprise features are paid"
],
"last_commit": "2026-02-09T10:00:00Z",
"language": "PHP",
"license": "GPLv2",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=orangehrm.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/orangehrm"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "m365",
"name": "Microsoft 365",
"category": "Productivity",
"is_open_source": false,
"pricing_model": "Paid (Subscription)",
"website": "https://www.office.com",
"description": "The world's most popular office suite and cloud collaboration platform.",
"alternatives": [
"onlyoffice"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=office.com",
"avg_monthly_cost": 12,
"pros": [
"Full productivity suite (Word, Excel, Teams)",
"Deep enterprise integration",
"1TB OneDrive storage included",
"Regular AI feature updates (Copilot)"
],
"cons": [
"Subscription fatigue \u2014 perpetual payments",
"Teams can be resource-heavy",
"Complex licensing tiers"
]
},
{
"slug": "onlyoffice",
"name": "ONLYOFFICE",
"category": "Productivity",
"is_open_source": true,
"github_repo": "ONLYOFFICE/DocumentServer",
"stars": 11000,
"website": "https://www.onlyoffice.com",
"description": "Powerful online document editors for text, spreadsheets, and presentations. Highly compatible with MS Office.",
"pros": [
"Full-featured collaborative editing for docs, sheets, and slides",
"Drop-in MS Office compatibility with high-fidelity rendering",
"Self-hosted integration with Nextcloud, Seafile, and more"
],
"cons": [
"Self-hosting can be complex"
],
"last_commit": "2026-02-09T15:30:00Z",
"language": "JavaScript",
"license": "AGPLv3",
"logo_url": "/logos/onlyoffice.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/onlyoffice"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "shopify",
"name": "Shopify",
"category": "E-commerce",
"is_open_source": false,
"pricing_model": "Paid (Subscription)",
"website": "https://www.shopify.com",
"description": "Commerical platform that allows anyone to set up an online store.",
"alternatives": [
"medusa"
],
"logo_url": "/logos/shopify.svg",
"avg_monthly_cost": 39,
"pros": [
"Easiest way to start selling online",
"Beautiful themes and fast checkout",
"Apps for almost any e-commerce need",
"Handles payments, shipping, and taxes"
],
"cons": [
"Transaction fees unless using Shopify Payments",
"Monthly costs add up with apps",
"Limited customization vs self-hosted solutions"
]
},
{
"slug": "medusa",
"name": "Medusa.js",
"category": "E-commerce",
"is_open_source": true,
"github_repo": "medusajs/medusa",
"stars": 24000,
"website": "https://medusajs.com",
"description": "The open-source alternative to Shopify. Building blocks for digital commerce.",
"pros": [
"Headless commerce with extreme flexibility for custom storefronts",
"Plugin architecture for payments, fulfillment, and CMS",
"Multi-region and multi-currency support built in"
],
"cons": [
"Requires developer knowledge"
],
"last_commit": "2026-02-09T16:45:00Z",
"language": "TypeScript",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=medusajs.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/medusa"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "docusign",
"name": "DocuSign",
"category": "Legal",
"is_open_source": false,
"pricing_model": "Paid (Envelope-based)",
"website": "https://www.docusign.com",
"description": "The world's #1 way to sign electronically on practically any device, from almost anywhere, at any time.",
"alternatives": [
"documenso"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=docusign.com",
"avg_monthly_cost": 25,
"pros": [
"Industry standard for e-signatures",
"Legally binding in most countries",
"Workflow automation for document routing",
"Strong mobile experience"
],
"cons": [
"Expensive for occasional use",
"UI feels dated compared to competitors",
"Limited free tier"
]
},
{
"slug": "documenso",
"name": "Documenso",
"category": "Legal",
"is_open_source": true,
"github_repo": "documenso/documenso",
"stars": 8000,
"website": "https://documenso.com",
"description": "The open-source DocuSign alternative. We aim to be the world's most trusted document signing platform.",
"pros": [
"Self-hosted digital signatures with full audit trail",
"Developer-friendly API and webhook integration",
"Beautiful, modern signing experience"
],
"cons": [
"Newer ecosystem"
],
"last_commit": "2026-02-10T09:00:00Z",
"language": "TypeScript",
"license": "AGPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=documenso.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/documenso"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mailchimp",
"name": "Mailchimp",
"category": "Marketing",
"is_open_source": false,
"pricing_model": "Paid (Contact-based)",
"website": "https://mailchimp.com",
"description": "All-in-one marketing platform that helps you manage and talk to your clients, customers, and other interested parties.",
"alternatives": [
"listmonk",
"mautic"
],
"logo_url": "/logos/mailchimp.svg",
"avg_monthly_cost": 13,
"pros": [
"Beginner-friendly email marketing",
"Good free tier for small lists",
"Built-in landing page builder",
"Detailed campaign analytics"
],
"cons": [
"Pricing increases steeply with list size",
"Owned by Intuit (less indie-friendly)",
"Template editor is limiting"
]
},
{
"slug": "listmonk",
"name": "Listmonk",
"category": "Marketing",
"is_open_source": true,
"github_repo": "knadh/listmonk",
"stars": 19000,
"website": "https://listmonk.app",
"description": "High performance, self-hosted newsletter and mailing list manager with a modern dashboard.",
"pros": [
"Handles millions of subscribers with blazing fast performance",
"Templating engine with rich media and personalization",
"Manages bounces, unsubscribes, and analytics automatically"
],
"cons": [
"No built-in sending (needs SMTP/SES)"
],
"last_commit": "2026-02-05T12:00:00Z",
"language": "Go",
"license": "AGPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=listmonk.app",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/listmonk"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mautic",
"name": "Mautic",
"category": "Marketing",
"is_open_source": true,
"github_repo": "mautic/mautic",
"stars": 7000,
"website": "https://www.mautic.org",
"description": "World's largest open source marketing automation project.",
"pros": [
"Full marketing automation with CRM-grade contact management",
"Visual campaign builder with multi-channel triggers",
"Email, SMS, and social media campaign support"
],
"cons": [
"Complex setup and maintenance"
],
"last_commit": "2026-02-09T18:00:00Z",
"language": "PHP",
"license": "GPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=mautic.org",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/mautic"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "statuspage",
"name": "Statuspage",
"category": "Monitoring",
"is_open_source": false,
"pricing_model": "Paid (Atlassian)",
"website": "https://www.atlassian.com/software/statuspage",
"description": "The best way to communicate status and downtime to your customers.",
"alternatives": [
"uptime-kuma"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=atlassian.com",
"avg_monthly_cost": 29,
"pros": [
"Clean, professional status pages",
"Integrated incident management",
"Email/SMS subscriber notifications",
"Atlassian ecosystem integration"
],
"cons": [
"Expensive for what it does ($29+/mo)",
"Limited customization options",
"Overkill if you just need a simple status page"
]
},
{
"slug": "uptime-kuma",
"name": "Uptime Kuma",
"category": "Monitoring",
"is_open_source": true,
"github_repo": "louislam/uptime-kuma",
"stars": 55000,
"website": "https://uptime.kuma.pet",
"description": "A fancy self-hosted monitoring tool.",
"pros": [
"Beautiful, real-time monitoring dashboard",
"Multi-protocol support: HTTP, TCP, DNS, Docker, and more",
"Notification integrations with 90+ services including Slack, Discord, and Telegram"
],
"cons": [
"Self-hosted only (usually)"
],
"last_commit": "2026-02-10T08:00:00Z",
"language": "JavaScript",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=uptime.kuma.pet",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/uptime-kuma"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "datadog",
"name": "Datadog",
"category": "Monitoring",
"is_open_source": false,
"pricing_model": "Paid (Usage-based)",
"website": "https://www.datadoghq.com",
"description": "Modern monitoring and security that gives you full visibility into your applications and infrastructure.",
"alternatives": [
"signoz"
],
"logo_url": "/logos/datadog.svg",
"avg_monthly_cost": 23,
"pros": [
"Comprehensive observability platform",
"APM, logs, metrics in one place",
"Excellent dashboards and alerting",
"Supports 750+ integrations"
],
"cons": [
"Notoriously expensive at scale",
"Complex pricing model (per host, per GB)",
"Can become a significant budget item"
]
},
{
"slug": "signoz",
"name": "SigNoz",
"category": "Monitoring",
"is_open_source": true,
"github_repo": "signoz/signoz",
"stars": 18000,
"website": "https://signoz.io",
"description": "Open source observability platform. SigNoz helps developers monitor applications and troubleshoot problems.",
"pros": [
"Unified metrics, traces, and logs in a single platform",
"OpenTelemetry native \u2014 no proprietary agents required",
"ClickHouse-powered for fast queries at scale"
],
"cons": [
"High resource usage (ClickHouse)"
],
"last_commit": "2026-02-09T20:00:00Z",
"language": "Go",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=signoz.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/signoz"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "typeform",
"name": "Typeform",
"category": "Productivity",
"is_open_source": false,
"pricing_model": "Paid (Response-based)",
"website": "https://www.typeform.com",
"description": "Build beautiful, interactive forms, surveys, quizzes, and something else entirely.",
"alternatives": [
"tally"
],
"logo_url": "/logos/typeform.svg",
"avg_monthly_cost": 25,
"pros": [
"Beautiful, conversational form experience",
"High completion rates vs traditional forms",
"Logic jumps and conditional flows",
"Great integrations (Zapier, webhooks)"
],
"cons": [
"Expensive for the response limits",
"Limited free tier (10 responses/mo)",
"Not ideal for complex multi-page forms"
]
},
{
"slug": "tally",
"name": "Tally",
"category": "Productivity",
"is_open_source": false,
"is_free_tier_generous": true,
"pricing_model": "Free/Paid",
"website": "https://tally.so",
"description": "The simplest way to create forms. Tally is a new type of form builder that works like a doc.",
"pros": [
"Notion-like form building experience with no-code simplicity",
"Unlimited forms and responses on the free tier",
"Conditional logic, hidden fields, and payment collection"
],
"cons": [
"Wait, it's not open source (but highly OS-friendly community)"
],
"tags": [
"Forms",
"Surveys",
"No-code"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=tally.so"
},
{
"slug": "confluence",
"name": "Confluence",
"category": "Productivity",
"is_open_source": false,
"pricing_model": "Paid (Atlassian)",
"website": "https://www.atlassian.com/software/confluence",
"description": "Your remote-friendly team workspace where knowledge and collaboration meet.",
"alternatives": [
"outline"
],
"logo_url": "/logos/confluence.svg",
"avg_monthly_cost": 10,
"pros": [
"Deep Jira integration for dev teams",
"Structured knowledge base with spaces",
"Templates for common documentation",
"Permissions and access control"
],
"cons": [
"Slow and bloated interface",
"Search is frustratingly poor",
"Editing experience lags behind Notion"
]
},
{
"slug": "outline",
"name": "Outline",
"category": "Productivity",
"is_open_source": true,
"github_repo": "outline/outline",
"stars": 24000,
"website": "https://www.getoutline.com",
"description": "Fast, collaborative, knowledge base for your team built using React and Markdown.",
"pros": [
"Sub-second search across all documents",
"Beautifully designed editor with Markdown shortcuts",
"Integrates with Slack, Figma, and 20+ tools out of the box"
],
"cons": [
"Hard to self-host (complex storage requirements)"
],
"last_commit": "2026-02-10T12:00:00Z",
"language": "TypeScript",
"license": "Other",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=getoutline.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/outline"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "hootsuite",
"name": "Hootsuite",
"category": "Marketing",
"is_open_source": false,
"pricing_model": "Paid (Seat-based)",
"website": "https://www.hootsuite.com",
"description": "Social media marketing and management dashboard.",
"alternatives": [
"mixpost"
],
"logo_url": "/logos/hootsuite.svg",
"avg_monthly_cost": 49,
"pros": [
"Manage multiple social accounts in one place",
"Post scheduling across platforms",
"Team collaboration and approval workflows",
"Analytics and reporting dashboard"
],
"cons": [
"Expensive plans ($99+/mo)",
"UI feels cluttered and dated",
"Free plan was eliminated"
]
},
{
"slug": "mixpost",
"name": "Mixpost",
"category": "Marketing",
"is_open_source": true,
"github_repo": "inovector/mixpost",
"stars": 3000,
"website": "https://mixpost.app",
"description": "Self-hosted social media management software.",
"pros": [
"Own your data",
"No monthly subscription"
],
"cons": [
"Newer, fewer social connectors"
],
"last_commit": "2026-02-01T15:00:00Z",
"language": "PHP",
"license": "Other",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=mixpost.app",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/mixpost"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "codespaces",
"name": "GitHub Codespaces",
"category": "DevOps",
"is_open_source": false,
"pricing_model": "Paid (Usage-based)",
"website": "https://github.com/features/codespaces",
"description": "Fast, cloud-hosted developer environments.",
"alternatives": [
"coder"
],
"logo_url": "/logos/codespaces.svg",
"avg_monthly_cost": 15,
"pros": [
"Full VS Code in the browser",
"Pre-configured dev environments",
"Instant onboarding for new contributors",
"Deep GitHub integration"
],
"cons": [
"Usage-based pricing adds up",
"Requires stable internet connection",
"Limited GPU/compute options"
]
},
{
"slug": "coder",
"name": "Coder",
"category": "DevOps",
"is_open_source": true,
"github_repo": "coder/coder",
"stars": 20000,
"website": "https://coder.com",
"description": "Provision software development environments as code on your infrastructure.",
"pros": [
"Run dev environments on any infrastructure \u2014 cloud, on-prem, or hybrid",
"Self-hosted remote development with VS Code and JetBrains support",
"Ephemeral workspaces with Terraform-based provisioning"
],
"cons": [
"Requires K8s or Terraform knowledge"
],
"last_commit": "2026-02-09T22:00:00Z",
"language": "Go",
"license": "AGPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=coder.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/coder"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "quickbooks",
"name": "QuickBooks",
"category": "Financial",
"is_open_source": false,
"pricing_model": "Paid (Monthly Subscription)",
"website": "https://quickbooks.intuit.com",
"description": "Smart, simple online accounting software for small businesses.",
"alternatives": [
"akaunting",
"erpnext"
],
"logo_url": "/logos/quickbooks.svg",
"avg_monthly_cost": 25,
"pros": [
"Industry standard for small business accounting",
"Easy invoicing and expense tracking",
"Bank feed integration",
"Tax preparation features"
],
"cons": [
"Subscription pricing keeps increasing",
"Performance issues with large files",
"Limited multi-currency support"
]
},
{
"slug": "akaunting",
"name": "Akaunting",
"category": "Financial",
"is_open_source": true,
"github_repo": "akaunting/akaunting",
"stars": 12000,
"website": "https://akaunting.com",
"description": "Free and open source online accounting software for small businesses and freelancers.",
"pros": [
"Modular app store",
"Multilingual and multicurrency"
],
"cons": [
"Some essential apps are paid"
],
"last_commit": "2026-02-08T14:00:00Z",
"language": "PHP",
"license": "GPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=akaunting.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/akaunting"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "premiere",
"name": "Adobe Premiere Pro",
"category": "Creative",
"is_open_source": false,
"pricing_model": "Paid (Creative Cloud)",
"website": "https://www.adobe.com/products/premiere.html",
"description": "Industry-leading video editing software for film, TV, and the web.",
"alternatives": [
"kdenlive"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=adobe.com",
"avg_monthly_cost": 35,
"pros": [
"Professional-grade video editing",
"Excellent integration with After Effects",
"Industry standard in film and media",
"AI-powered features (scene detection, auto-reframe)"
],
"cons": [
"Subscription-only ($22.99/mo)",
"Resource-intensive \u2014 needs powerful hardware",
"Steep learning curve"
]
},
{
"slug": "kdenlive",
"name": "Kdenlive",
"category": "Creative",
"is_open_source": true,
"github_repo": "KDE/kdenlive",
"stars": 3500,
"website": "https://kdenlive.org",
"description": "Open source video editing software based on the MLT Framework and KDE.",
"pros": [
"Truly free forever",
"Powerful multi-track editing"
],
"cons": [
"UI can be intimidating for beginners"
],
"last_commit": "2026-02-10T11:00:00Z",
"language": "C++",
"license": "GPL-3.0",
"logo_url": "/logos/kdenlive.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "dashlane",
"name": "Dashlane",
"category": "Security",
"is_open_source": false,
"pricing_model": "Paid (Subscription)",
"website": "https://www.dashlane.com",
"description": "Cloud-based password manager and digital wallet.",
"alternatives": [
"vaultwarden",
"bitwarden"
],
"logo_url": "/logos/dashlane.svg",
"avg_monthly_cost": 8,
"pros": [
"Clean, intuitive interface",
"Built-in VPN on premium plans",
"Dark web monitoring alerts",
"Secure sharing for teams"
],
"cons": [
"More expensive than competitors",
"Free tier limited to 25 passwords",
"Desktop app was discontinued"
]
},
{
"slug": "vaultwarden",
"name": "Vaultwarden",
"category": "Security",
"is_open_source": true,
"github_repo": "dani-garcia/vaultwarden",
"stars": 32000,
"website": "https://github.com/dani-garcia/vaultwarden",
"description": "Unofficial Bitwarden compatible server written in Rust, formerly known as bitwarden_rs.",
"pros": [
"Full Bitwarden API compatibility in a lightweight Rust binary",
"Runs on 50MB of RAM \u2014 perfect for Raspberry Pi or small VPS",
"Supports organizations, attachments, and Bitwarden Send"
],
"cons": [
"Third-party implementation (not security audited officially)"
],
"last_commit": "2026-02-09T10:00:00Z",
"language": "Rust",
"license": "AGPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=bitwarden.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/vaultwarden"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "pipedrive",
"name": "Pipedrive",
"category": "CRM",
"is_open_source": false,
"pricing_model": "Paid (Seat-based)",
"website": "https://www.pipedrive.com",
"description": "Sales CRM & pipeline management software that helps you get more organized.",
"alternatives": [
"twenty"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=pipedrive.com",
"avg_monthly_cost": 15,
"pros": [
"Simple, visual sales pipeline",
"Easy to set up and use",
"Good automation for follow-ups",
"Affordable entry-level pricing"
],
"cons": [
"Limited features vs Salesforce",
"Reporting could be more powerful",
"No free tier"
]
},
{
"slug": "twenty",
"name": "Twenty",
"category": "CRM",
"is_open_source": true,
"github_repo": "twentyhq/twenty",
"stars": 15000,
"website": "https://twenty.com",
"description": "A modern open-source CRM alternative to Salesforce and Pipedrive.",
"pros": [
"Clean, Notion-like interface for CRM workflows",
"Deeply customizable data models and views",
"GraphQL API for flexible integrations"
],
"cons": [
"Still in early development"
],
"last_commit": "2026-02-10T14:00:00Z",
"language": "TypeScript",
"license": "AGPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=twenty.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/twenty"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "sentry",
"name": "Sentry",
"category": "Monitoring",
"is_open_source": false,
"pricing_model": "Paid (Usage-based)",
"website": "https://sentry.io",
"description": "Developer-first error tracking and performance monitoring.",
"alternatives": [
"glitchtip"
],
"logo_url": "/logos/sentry.svg",
"avg_monthly_cost": 26,
"pros": [
"Best-in-class error tracking",
"Stack traces with source maps",
"Performance monitoring built in",
"Supports 100+ platforms and languages"
],
"cons": [
"Can be noisy without proper filtering",
"Pricing based on error volume",
"Self-hosting is complex"
]
},
{
"slug": "glitchtip",
"name": "GlitchTip",
"category": "Monitoring",
"is_open_source": true,
"github_repo": "glitchtip/glitchtip",
"stars": 3000,
"website": "https://glitchtip.com",
"description": "Open source error tracking that's compatible with Sentry SDKs.",
"pros": [
"Sentry-compatible error tracking that simplifies self-hosting",
"Lightweight alternative requiring minimal server resources",
"Performance monitoring with transaction tracking"
],
"cons": [
"Less polished UI than Sentry"
],
"last_commit": "2026-02-05T09:00:00Z",
"language": "Python",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=glitchtip.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/glitchtip"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "calendly",
"name": "Calendly",
"category": "Productivity",
"is_open_source": false,
"pricing_model": "Paid (Seat-based)",
"website": "https://calendly.com",
"description": "The modern scheduling platform that makes 'finding time' a breeze.",
"alternatives": [
"calcom",
"tymeslot"
],
"logo_url": "/logos/calendly.svg",
"avg_monthly_cost": 10,
"pros": [
"Frictionless scheduling experience",
"Integrates with Google/Outlook calendars",
"Team scheduling and round-robin",
"Customizable booking pages"
],
"cons": [
"Free plan limited to one event type",
"Premium features locked behind $10+/mo",
"Branding on free tier"
]
},
{
"slug": "calcom",
"name": "Cal.com",
"category": "Productivity",
"is_open_source": true,
"github_repo": "calcom/cal.com",
"stars": 30000,
"website": "https://cal.com",
"description": "The open-source Calendly alternative. Take control of your scheduling.",
"pros": [
"Self-hosted scheduling \u2014 no data leaves your server",
"Deeply extensible with a plugin architecture and API",
"Round-robin, collective, and managed event types"
],
"cons": [
"Can be overkill for simple use cases"
],
"last_commit": "2026-02-10T07:00:00Z",
"language": "TypeScript",
"license": "AGPL-3.0",
"logo_url": "/logos/calcom.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/calcom"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "intercom",
"name": "Intercom",
"category": "Support",
"is_open_source": false,
"pricing_model": "Paid (Seat-based)",
"website": "https://www.intercom.com",
"description": "The business messenger that builds real-time connections.",
"alternatives": [
"chaskiq"
],
"logo_url": "/logos/intercom.svg",
"avg_monthly_cost": 39,
"pros": [
"Best-in-class live chat and messaging",
"AI chatbot (Fin) handles common questions",
"Product tours and onboarding flows",
"Unified inbox for support"
],
"cons": [
"Very expensive ($74+/mo starting)",
"Pricing model is complex and confusing",
"Can be overkill for small teams"
]
},
{
"slug": "chaskiq",
"name": "Chaskiq",
"category": "Support",
"is_open_source": true,
"github_repo": "chaskiq/chaskiq",
"stars": 4000,
"website": "https://chaskiq.io",
"description": "Open source conversational marketing platform alternative to Intercom and Drift.",
"pros": [
"Self-hosted customer messaging that replaces Intercom",
"Bot automation with visual workflow builder",
"Multi-channel support including web chat, email, and WhatsApp"
],
"cons": [
"Smaller community than Chatwoot"
],
"last_commit": "2026-01-28T12:00:00Z",
"language": "Ruby",
"license": "GPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=chaskiq.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/chaskiq"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mailgun",
"name": "Mailgun",
"category": "Marketing",
"is_open_source": false,
"pricing_model": "Paid (Usage-based)",
"website": "https://www.mailgun.com",
"description": "Electronic mail delivery service for developers.",
"alternatives": [
"postal"
],
"logo_url": "/logos/mailgun.svg",
"avg_monthly_cost": 15,
"pros": [
"Reliable transactional email delivery",
"Powerful email API and SMTP relay",
"Detailed delivery analytics",
"Good documentation"
],
"cons": [
"No visual email builder",
"Pricing increased significantly",
"Support quality has declined"
]
},
{
"slug": "postal",
"name": "Postal",
"category": "Marketing",
"is_open_source": true,
"github_repo": "postalserver/postal",
"stars": 15000,
"website": "https://postalserver.io",
"description": "A fully featured open source mail delivery platform for incoming & outgoing e-mail.",
"pros": [
"High-performance mail delivery server built for throughput",
"Detailed delivery tracking with click and open analytics",
"IP pool management and DKIM/SPF configuration"
],
"cons": [
"Extremely complex to manage delivery (IP warm-up)"
],
"last_commit": "2026-02-09T13:00:00Z",
"language": "Ruby",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=postalserver.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/postal"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "segment",
"name": "Segment",
"category": "Marketing",
"is_open_source": false,
"pricing_model": "Paid (Usage-based)",
"website": "https://segment.com",
"description": "The leading customer data platform (CDP).",
"alternatives": [
"jitsu"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=segment.com",
"avg_monthly_cost": 120,
"pros": [
"Single API for all analytics tools",
"Customer data platform (CDP) capabilities",
"200+ destination integrations",
"Clean data pipeline management"
],
"cons": [
"Extremely expensive ($120+/mo to start)",
"Complex to set up properly",
"Overkill for simple tracking needs"
]
},
{
"slug": "jitsu",
"name": "Jitsu",
"category": "Marketing",
"is_open_source": true,
"github_repo": "jitsucom/jitsu",
"stars": 5000,
"website": "https://jitsu.com",
"description": "High-performance data collection platform and open-source Segment alternative.",
"pros": [
"Unlimited data volume",
"Real-time data streaming"
],
"cons": [
"Fewer destinations than Segment"
],
"last_commit": "2026-02-10T16:00:00Z",
"language": "TypeScript",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=jitsu.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/jitsu"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "dokku",
"name": "Dokku",
"category": "DevOps",
"is_open_source": true,
"github_repo": "dokku/dokku",
"website": "https://dokku.com",
"description": "A docker-powered PaaS that helps you build and manage the lifecycle of applications",
"pros": [
"Rock-solid stability \u2014 battle-tested since 2013",
"Heroku-compatible buildpacks and Procfile workflow",
"Zero-downtime deploys with simple git push"
],
"cons": [
"CLI driven"
],
"stars": 31874,
"last_commit": "2026-02-09T15:40:31Z",
"language": "Shell",
"license": "MIT License",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=dokku.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/dokku"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "chatgpt",
"name": "ChatGPT / OpenAI",
"category": "AI Models",
"is_open_source": false,
"pricing_model": "Paid/Freemium",
"website": "https://openai.com",
"description": "The leading commercial AI assistant and API platform (GPT-4o, o1).",
"alternatives": [
"llama",
"deepseek",
"mistral"
],
"tags": [
"AI",
"LLM",
"Chat"
],
"hosting_type": "cloud",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=openai.com",
"avg_monthly_cost": 20,
"pros": [
"Most capable general-purpose AI assistant",
"Excellent at writing, coding, and reasoning",
"Plugin ecosystem and GPT store",
"Supports image, voice, and file inputs"
],
"cons": [
"$20/mo for GPT-4 access",
"Can hallucinate confidently",
"No self-hosting option",
"Data privacy concerns for sensitive info"
]
},
{
"slug": "llama",
"name": "Meta Llama 3.1",
"category": "AI Models",
"is_open_source": true,
"github_repo": "meta-llama/llama3",
"website": "https://llama.meta.com",
"description": "Meta's flagship open-weight model with 128K context. Supports 8B, 70B, and 405B parameters.",
"pros": [
"Massive 128K token context window for long documents",
"Strong multilingual support across 8+ languages",
"SOTA 405B variant competing with GPT-4 at a fraction of the cost"
],
"cons": [
"405B requires massive hardware",
"Llama Community License"
],
"stars": 65000,
"language": "Python",
"license": "Llama 3.1 Community License",
"tags": [
"AI",
"LLM",
"128K Context"
],
"hardware_req": "8GB VRAM (8B), 40GB+ VRAM (70B), 800GB+ VRAM (405B)",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 128000,
"parameters_total_b": 405,
"is_multimodal": false
},
"logo_url": "/logos/meta.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/llama"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek",
"name": "DeepSeek-V3 / R1",
"category": "AI Models",
"is_open_source": true,
"github_repo": "deepseek-ai/DeepSeek-V3",
"website": "https://deepseek.com",
"description": "Powerful open-source models including V3 (671B) and R1 (Reasoning). Rivals GPT-4o and o1.",
"pros": [
"State-of-the-art reasoning (R1)",
"Extremely cost efficient",
"MIT License (V3/R1)"
],
"cons": [
"Full model requires huge VRAM",
"Newer ecosystem"
],
"stars": 110000,
"language": "Python",
"license": "MIT License",
"tags": [
"AI",
"LLM",
"Reasoning"
],
"alternatives": [
"llama",
"mistral",
"qwen",
"deepseek-v3-1"
],
"hardware_req": "8GB VRAM (Distilled), 160GB+ VRAM (Full)",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 160,
"context_window_tokens": 128000,
"parameters_total_b": 671,
"parameters_active_b": 37,
"is_multimodal": false
},
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=deepseek.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/deepseek"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mistral",
"name": "Mistral Large 2",
"category": "AI Models",
"is_open_source": true,
"github_repo": "mistralai/mistral-inference",
"website": "https://mistral.ai",
"description": "Flagship 123B model from Mistral AI. Optimized for multilingual, reasoning, and coding tasks.",
"pros": [
"State-of-the-art performance per parameter on benchmarks",
"128K context window with function-calling support",
"Efficient Mixture-of-Experts architecture for fast inference"
],
"cons": [
"Mistral Research License",
"Requires high VRAM (80GB+)"
],
"stars": 20000,
"language": "Python",
"license": "Mistral Research License",
"tags": [
"AI",
"LLM",
"EU"
],
"hardware_req": "80GB+ VRAM (FP16), 40GB+ (8-bit)",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 80,
"context_window_tokens": 128000,
"parameters_total_b": 123,
"is_multimodal": false
},
"logo_url": "/logos/mistral.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/mistral"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "gemma",
"name": "Google Gemma 2",
"category": "AI Models",
"is_open_source": true,
"github_repo": "google/gemma-2",
"website": "https://ai.google.dev/gemma",
"description": "Google's open-weight models (9B, 27B) with class-leading performance and efficient architecture.",
"pros": [
"Distilled for performance",
"Excellent 27B variant",
"Google AI ecosystem"
],
"cons": [
"8K context window",
"Gemma Terms of Use"
],
"stars": 20000,
"language": "Python",
"license": "Gemma License",
"tags": [
"AI",
"LLM",
"Google"
],
"hardware_req": "8GB VRAM (9B), 24GB+ VRAM (27B)",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 18,
"context_window_tokens": 8192,
"parameters_total_b": 27,
"is_multimodal": false
},
"logo_url": "/logos/gemma.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/gemma"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "qwen",
"name": "Qwen 2.5",
"category": "AI Models",
"is_open_source": true,
"github_repo": "QwenLM/Qwen2.5",
"website": "https://qwenlm.github.io",
"description": "Comprehensive LLM series from Alibaba Cloud, excelling in coding, math, and multilingual support.",
"pros": [
"128K context window",
"Top-tier coding ability",
"Apache 2.0 (mostly)"
],
"cons": [
"72B requires significant VRAM"
],
"stars": 50000,
"language": "Python",
"license": "Apache License 2.0",
"tags": [
"AI",
"LLM",
"Coding"
],
"hardware_req": "8GB VRAM (7B), 40GB+ VRAM (32B), 140GB+ VRAM (72B)",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 40,
"context_window_tokens": 128000,
"parameters_total_b": 72,
"is_multimodal": false
},
"logo_url": "/logos/qwen.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/qwen"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "midjourney",
"name": "Midjourney",
"category": "AI Image Generation",
"is_open_source": false,
"pricing_model": "Paid (Subscription)",
"website": "https://midjourney.com",
"description": "Leading AI image generation tool, known for artistic and photorealistic outputs.",
"alternatives": [
"stable-diffusion",
"flux"
],
"tags": [
"AI",
"Image",
"Art"
],
"hosting_type": "cloud",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=midjourney.com",
"avg_monthly_cost": 10,
"pros": [
"Best-in-class AI image generation quality",
"Stunning artistic and photorealistic outputs",
"Active community for inspiration",
"V6 handles text in images well"
],
"cons": [
"Discord-only interface (no standalone app)",
"No free tier ($10/mo minimum)",
"Limited control over exact outputs",
"No API for automation"
]
},
{
"slug": "stable-diffusion",
"name": "Stable Diffusion 3.5",
"category": "AI Image Generation",
"is_open_source": true,
"github_repo": "Stability-AI/sd3.5",
"website": "https://stability.ai",
"description": "The latest open-weights image generation model from Stability AI, offering superior prompt adherence.",
"pros": [
"Run image generation entirely on your own GPU",
"Extensive community with thousands of fine-tuned models",
"ControlNet, inpainting, and img2img for precise creative control"
],
"cons": [
"Stability Community License",
"Requires 8GB+ VRAM"
],
"stars": 10000,
"language": "Python",
"license": "Stability Community License",
"tags": [
"AI",
"Image",
"Prompt Adherence"
],
"hardware_req": "8GB VRAM (Medium), 16GB+ VRAM (Large)",
"hosting_type": "self-hosted",
"logo_url": "/logos/stability.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/stable-diffusion"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mochi-1",
"name": "Mochi-1",
"category": "AI Video Generation",
"is_open_source": true,
"github_repo": "genmoai/mochi1",
"website": "https://www.genmo.ai",
"description": "High-fidelity open-weights video generation model from Genmo, rivaling closed-source alternatives.",
"pros": [
"Realistic motion",
"Adobe-like quality",
"Apache 2.0 license"
],
"cons": [
"Extreme hardware requirements",
"Memory intensive"
],
"stars": 5000,
"language": "Python",
"license": "Apache License 2.0",
"tags": [
"AI",
"Video",
"Motion"
],
"hardware_req": "24GB VRAM (Minimal), 80GB VRAM (Recommended)",
"hosting_type": "both",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=genmo.ai",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "hunyuan-video",
"name": "HunyuanVideo 1.5",
"category": "AI Video Generation",
"is_open_source": true,
"github_repo": "Tencent/HunyuanVideo",
"website": "https://github.com/Tencent/HunyuanVideo",
"description": "Tencent's state-of-the-art open-source video generation model with 13B parameters.",
"pros": [
"Native 720p output",
"Long sequences support",
"Stable and clean motion"
],
"cons": [
"High compute cost"
],
"stars": 8000,
"language": "Python",
"license": "Apache License 2.0",
"tags": [
"AI",
"Video",
"HD"
],
"hardware_req": "14GB VRAM (v1.5/distilled), 45GB+ VRAM (Base)",
"hosting_type": "both",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=tencent.com",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "flux",
"name": "FLUX",
"category": "AI Image Generation",
"is_open_source": true,
"github_repo": "black-forest-labs/flux",
"website": "https://blackforestlabs.ai",
"description": "Next-gen open image generation model from Black Forest Labs. State-of-the-art quality rivaling Midjourney.",
"pros": [
"Outstanding image quality",
"Open weights available",
"Rapid community adoption"
],
"cons": [
"High VRAM requirement",
"Newer (less tooling)"
],
"stars": 20000,
"language": "Python",
"license": "Apache License 2.0",
"tags": [
"AI",
"Image",
"New"
],
"hardware_req": "12GB+ VRAM (Schnell), 24GB+ (Dev)",
"hosting_type": "both",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=blackforestlabs.ai",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "github-copilot",
"name": "GitHub Copilot",
"category": "AI Coding",
"is_open_source": false,
"pricing_model": "Paid (Subscription)",
"website": "https://github.com/features/copilot",
"description": "AI pair programmer by GitHub/OpenAI. Integrates into VS Code and JetBrains.",
"alternatives": [
"continue-dev",
"tabby"
],
"tags": [
"AI",
"Coding",
"IDE"
],
"hosting_type": "cloud",
"logo_url": "/logos/github-copilot.svg",
"avg_monthly_cost": 10,
"pros": [
"Best AI code completion in the market",
"Deep IDE integration (VS Code, JetBrains)",
"Understands project context",
"Copilot Chat for code explanations"
],
"cons": [
"$10/mo per user",
"Can suggest insecure or outdated patterns",
"Privacy concerns with code telemetry",
"Dependent on GitHub/Microsoft"
]
},
{
"slug": "continue-dev",
"name": "Continue",
"category": "AI Coding",
"is_open_source": true,
"github_repo": "continuedev/continue",
"website": "https://continue.dev",
"description": "Open-source AI code assistant for VS Code and JetBrains. Use any model (local or API).",
"pros": [
"Highly customizable AI coding assistant \u2014 bring your own model",
"Works with VS Code and JetBrains natively",
"Context-aware with codebase indexing and retrieval"
],
"cons": [
"Requires model setup"
],
"stars": 25000,
"language": "TypeScript",
"license": "Apache License 2.0",
"tags": [
"AI",
"Coding",
"IDE",
"Self-Hosted"
],
"hardware_req": "Depends on chosen model",
"hosting_type": "both",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=continue.dev",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "tabby",
"name": "TabbyML",
"category": "AI Coding",
"is_open_source": true,
"github_repo": "TabbyML/tabby",
"website": "https://tabby.tabbyml.com",
"description": "Self-hosted AI coding assistant. An open-source, self-hosted alternative to GitHub Copilot.",
"pros": [
"Enterprise-ready self-hosted code completion",
"Supports multiple model backends including local GGUF",
"IDE extensions for VS Code, Vim, and IntelliJ"
],
"cons": [
"Needs GPU for best results"
],
"stars": 25000,
"language": "Rust",
"license": "Apache License 2.0",
"tags": [
"AI",
"Coding",
"Self-Hosted"
],
"hardware_req": "8GB+ VRAM recommended",
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=tabby.tabbyml.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/tabby"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "ollama",
"name": "Ollama",
"category": "AI Runners",
"is_open_source": true,
"github_repo": "ollama/ollama",
"website": "https://ollama.com",
"description": "Get up and running with Llama 3, Mistral, Gemma, and other large language models locally.",
"pros": [
"Run any open model locally with a single command",
"OpenAI-compatible API for drop-in integration",
"Automatic model management with quantization support"
],
"cons": [
"Command line focused (needs UI)"
],
"stars": 60000,
"language": "Go",
"license": "MIT License",
"tags": [
"AI",
"Local",
"Runner"
],
"hardware_req": "8GB+ RAM",
"hosting_type": "self-hosted",
"logo_url": "/logos/ollama.svg",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/ollama"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "open-webui",
"name": "Open WebUI",
"category": "AI Interfaces",
"is_open_source": true,
"github_repo": "open-webui/open-webui",
"website": "https://openwebui.com",
"description": "User-friendly WebUI for LLMs (Formerly Ollama WebUI). Supports Ollama and OpenAI-compatible APIs.",
"pros": [
"ChatGPT-like UI",
"Multi-model chat",
"RAG support"
],
"cons": [
"Requires backend (like Ollama)"
],
"stars": 15000,
"language": "Svelte",
"license": "MIT License",
"tags": [
"AI",
"UI",
"Chat"
],
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=openwebui.com",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "jan",
"name": "Jan",
"category": "AI Interfaces",
"is_open_source": true,
"github_repo": "janhq/jan",
"website": "https://jan.ai",
"description": "Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.",
"pros": [
"Runs offline",
"Native app (no Docker)",
"Local model manager"
],
"cons": [
"Heavy resource usage"
],
"stars": 18000,
"language": "TypeScript",
"license": "AGPL-3.0",
"tags": [
"AI",
"Desktop",
"Offline"
],
"hardware_req": "Apple Silicon or NVIDIA GPU",
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=jan.ai",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "lm-studio",
"name": "LM Studio",
"category": "AI Runners",
"is_open_source": false,
"pricing_model": "Free (Proprietary)",
"website": "https://lmstudio.ai",
"description": "Discover, download, and run local LLMs. Easy GUI for GGUF models.",
"alternatives": [
"ollama",
"gpt4all"
],
"tags": [
"AI",
"Desktop",
"GUI"
],
"hardware_req": "Apple Silicon or NVIDIA/AMD GPU",
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=lmstudio.ai",
"referral_url": "https://m.do.co/c/2ed27757a361",
"pros": [
"Run LLMs locally with a clean GUI",
"No cloud dependency \u2014 fully offline",
"Supports GGUF and other quantized formats",
"Built-in model discovery and download"
],
"cons": [
"Requires decent hardware (8GB+ RAM)",
"Closed source despite local-first approach",
"Limited compared to CLI tools like Ollama"
]
},
{
"slug": "gpt4all",
"name": "GPT4All",
"category": "AI Runners",
"is_open_source": true,
"github_repo": "nomic-ai/gpt4all",
"website": "https://gpt4all.io",
"description": "Run open-source LLMs locally on your CPU and GPU. No internet required.",
"pros": [
"One-click desktop installer \u2014 no terminal needed",
"Built-in RAG for chatting with your local documents",
"Runs on CPU \u2014 no GPU required for basic models"
],
"cons": [
"Slower on CPU"
],
"stars": 65000,
"language": "C++",
"license": "Apache License 2.0",
"tags": [
"AI",
"Desktop",
"CPU"
],
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=gpt4all.io",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/gpt4all"
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "localai",
"name": "LocalAI",
"category": "AI Runners",
"is_open_source": true,
"github_repo": "mudler/LocalAI",
"website": "https://localai.io",
"description": "The specific build of LocalAI, the free, Open Source OpenAI alternative. Drop-in replacement for OpenAI API.",
"pros": [
"OpenAI API compatible",
"Runs on consumer hardware",
"No GPU required"
],
"cons": [
"Configuration heavy"
],
"stars": 20000,
"language": "Go",
"license": "MIT License",
"tags": [
"AI",
"API",
"Backend"
],
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=localai.io",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "flowise",
"name": "Flowise",
"category": "AI Tools",
"is_open_source": true,
"github_repo": "FlowiseAI/Flowise",
"website": "https://flowiseai.com",
"description": "Drag & drop UI to build your customized LLM flow using LangChainJS.",
"pros": [
"Low-code",
"Visual builder",
"Rich integrations"
],
"cons": [
"Node.js dependency"
],
"stars": 28000,
"language": "TypeScript",
"license": "Apache License 2.0",
"tags": [
"AI",
"Low-Code",
"LangChain"
],
"hosting_type": "self-hosted",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=flowiseai.com",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "llama-4",
"name": "Meta Llama 4",
"category": "AI Models",
"is_open_source": true,
"github_repo": "meta-llama/llama4",
"website": "https://llama.meta.com",
"description": "The latest generation of Llama. 'Maverick' architecture with 256K context. The new standard for open weights.",
"pros": [
"Next-gen Maverick architecture \u2014 faster and smarter than Llama 3",
"256K context window \u2014 double that of most competitors",
"Native multimodal support for images, video, and text"
],
"cons": [
"High VRAM for top tiers"
],
"stars": 45000,
"language": "Python",
"license": "Llama Community License",
"tags": [
"AI",
"LLM",
"2026",
"SOTA"
],
"hardware_req": "12GB VRAM (Medium), 48GB+ VRAM (Large)",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 12,
"context_window_tokens": 256000,
"parameters_total_b": 65,
"is_multimodal": true
},
"logo_url": "/logos/meta.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "gemma-3",
"name": "Google Gemma 3",
"category": "AI Models",
"is_open_source": true,
"github_repo": "google/gemma-3",
"website": "https://ai.google.dev/gemma",
"description": "Gemma 3 (27B) delivers GPT-5 class performance on a single GPU. Optimized for reasoning and agents.",
"pros": [
"Incredible 27B performance",
"Agent-centric design",
"JAX/PyTorch native"
],
"cons": [
"limited to 27B size currently"
],
"stars": 15000,
"language": "Python",
"license": "Gemma License",
"tags": [
"AI",
"LLM",
"Google",
"2026"
],
"hardware_req": "24GB VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 1000000,
"parameters_total_b": 27,
"is_multimodal": true
},
"logo_url": "/logos/gemma.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "qwen-3",
"name": "Qwen 3 (235B)",
"category": "AI Models",
"is_open_source": true,
"github_repo": "QwenLM/Qwen3",
"website": "https://qwenlm.github.io",
"description": "Massive 235B param model. The absolute king of coding and mathematics benchmarks in 2026.",
"pros": [
"Unmatched coding performance",
"Excellent math/reasoning",
"MoE efficiency"
],
"cons": [
"Requires multi-GPU setup"
],
"stars": 35000,
"language": "Python",
"license": "Apache License 2.0",
"tags": [
"AI",
"LLM",
"Coding",
"MoE"
],
"hardware_req": "140GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 140,
"context_window_tokens": 1000000,
"parameters_total_b": 235,
"is_multimodal": false
},
"logo_url": "/logos/qwen.svg",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek-v3-1",
"name": "DeepSeek V3.1",
"category": "AI Models",
"is_open_source": true,
"github_repo": "deepseek-ai/DeepSeek-V3.1",
"website": "https://deepseek.com",
"description": "Refined V3 architecture with improved instruction following and reduced hallucination rates.",
"pros": [
"API pricing 10-50x cheaper than GPT-4 equivalents",
"Open weights with full model access \u2014 no API lock-in",
"Top-tier reasoning that rivals closed-source frontier models"
],
"cons": [
"Complex serving stack"
],
"stars": 120000,
"language": "Python",
"license": "MIT License",
"tags": [
"AI",
"LLM",
"Reasoning"
],
"alternatives": [
"deepseek",
"llama",
"mistral",
"qwen"
],
"hardware_req": "80GB VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 80,
"context_window_tokens": 128000,
"parameters_total_b": 685,
"is_multimodal": false
},
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=deepseek.com",
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "llama-3-1-8b",
"name": "Llama 3.1 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "The latest 8B parameter model from Meta, optimized for efficiency and edge devices.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 128000,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-3-1-70b",
"name": "Llama 3.1 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "A powerful 70B model by Meta, rivaling closed-source top-tier models.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 128000,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-3-1-405b",
"name": "Llama 3.1 405B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "Meta's massive 405B frontier-class open weights model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "284GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 284,
"context_window_tokens": 128000,
"parameters_total_b": 405,
"parameters_active_b": 405,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-3-8b",
"name": "Llama 3 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "Meta's highly capable 8B model, a standard for local LLM inference.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 8192,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-3-70b",
"name": "Llama 3 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "Meta's previous generation 70B heavy-hitter.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 8192,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-2-7b",
"name": "Llama 2 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "The classic 7B model that started the open-weight revolution.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-2-13b",
"name": "Llama 2 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "A balanced 13B model from the Llama 2 series.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-2-70b",
"name": "Llama 2 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "The largest Llama 2 model, widely used for fine-tuning.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "code-llama-7b",
"name": "Code Llama 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "Specialized coding model based on Llama 2.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 100000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "code-llama-13b",
"name": "Code Llama 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "Mid-sized specialized coding model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 100000,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "code-llama-34b",
"name": "Code Llama 34B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "Large coding model with excellent performance.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 100000,
"parameters_total_b": 34,
"parameters_active_b": 34,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "code-llama-70b",
"name": "Code Llama 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llama.meta.com",
"description": "The most powerful Code Llama variant.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Open Weights",
"AI",
"LLM",
"Meta"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 100000,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "mistral-7b-v0-3",
"name": "Mistral 7B v0.3",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "Updated 7B model from Mistral AI with extended vocabulary and function calling.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 32000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "mistral-nemo-12b",
"name": "Mistral Nemo 12B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "A native 12B model built in collaboration with NVIDIA, fitting in 24GB VRAM.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 128000,
"parameters_total_b": 12,
"parameters_active_b": 12,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "mixtral-8x7b",
"name": "Mixtral 8x7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "The first high-performance open sparse Mixture-of-Experts (MoE) model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "33GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 33,
"context_window_tokens": 32000,
"parameters_total_b": 47,
"parameters_active_b": 47,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "mixtral-8x22b",
"name": "Mixtral 8x22B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "A massive MoE model setting new standards for open weights.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "99GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 99,
"context_window_tokens": 65000,
"parameters_total_b": 141,
"parameters_active_b": 141,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "codestral-22b",
"name": "Codestral 22B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "Mistral's first dedicated code model, proficient in 80+ languages.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "15GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 15,
"context_window_tokens": 32000,
"parameters_total_b": 22,
"parameters_active_b": 22,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mathstral-7b",
"name": "Mathstral 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "Specialized model for math and reasoning tasks.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 32000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "ministral-3b",
"name": "Ministral 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "Mistral's efficient edge model for mobile and low-latency use cases.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 128000,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "ministral-8b",
"name": "Ministral 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://mistral.ai",
"description": "A powerful edge model bridging the gap between small and medium LLMs.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Europe",
"Mistral AI"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 128000,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "qwen-2-5-0-5b",
"name": "Qwen 2.5 0.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Tiny but capable model for extreme edge analytics.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 32000,
"parameters_total_b": 0.5,
"parameters_active_b": 0.5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-1-5b",
"name": "Qwen 2.5 1.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Small footprint model punching above its weight.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 32000,
"parameters_total_b": 1.5,
"parameters_active_b": 1.5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-3b",
"name": "Qwen 2.5 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Balanced 3B model, great for mobile inference.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 32000,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-7b",
"name": "Qwen 2.5 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "The 7B workhorse of the Qwen 2.5 family, beating Llama 3.1 8B in many benchmarks.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 128000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-14b",
"name": "Qwen 2.5 14B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "A sweet-spot size for dual-GPU or high VRAM consumer cards.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "10GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 128000,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-32b",
"name": "Qwen 2.5 32B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Ideally sized for 24GB VRAM cards like the RTX 3090/4090.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "22GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 128000,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-72b",
"name": "Qwen 2.5 72B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Top-tier open weights model, consistently ranking high on leaderboards.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "50GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 50,
"context_window_tokens": 128000,
"parameters_total_b": 72,
"parameters_active_b": 72,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-coder-1-5b",
"name": "Qwen 2.5 Coder 1.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Tiny coding assistant.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 32000,
"parameters_total_b": 1.5,
"parameters_active_b": 1.5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-coder-7b",
"name": "Qwen 2.5 Coder 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "State-of-the-art 7B coding model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 128000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-5-coder-32b",
"name": "Qwen 2.5 Coder 32B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Powerful coding model fitting in consumer hardware.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "22GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 128000,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-vl-7b",
"name": "Qwen 2 VL 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Vision-Language model capable of understanding images and video.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 32000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": true
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen-2-vl-72b",
"name": "Qwen 2 VL 72B",
"category": "AI Models",
"is_open_source": true,
"website": "https://qwenlm.github.io",
"description": "Massive Vision-Language model for complex visual reasoning.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Alibaba Cloud",
"Qwen",
"LLM",
"AI",
"Alibaba"
],
"hardware_req": "50GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 50,
"context_window_tokens": 32000,
"parameters_total_b": 72,
"parameters_active_b": 72,
"is_multimodal": true
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "gemma-2-2b",
"name": "Gemma 2 2B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Efficient 2B model by Google, distilled for high performance.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 8192,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "gemma-2-9b",
"name": "Gemma 2 9B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Google's powerful 9B open model, outperforming larger predecessors.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 8192,
"parameters_total_b": 9,
"parameters_active_b": 9,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "gemma-2-27b",
"name": "Gemma 2 27B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Large-scale open model from Google designed for complex reasoning.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "19GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 19,
"context_window_tokens": 8192,
"parameters_total_b": 27,
"parameters_active_b": 27,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "codegemma-2b",
"name": "CodeGemma 2B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Fast, lightweight code completion model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 8192,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "codegemma-7b",
"name": "CodeGemma 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Instruction-tuned coding model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 8192,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "recurrentgemma-2b",
"name": "RecurrentGemma 2B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Gemma architecture with recurrent neural network efficiency.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 8192,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "palette-2b",
"name": "Palette 2B",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.google.dev/gemma",
"description": "Specialized vision-language model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Gemma",
"Google",
"LLM",
"Google DeepMind",
"AI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 8192,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "phi-3-5-mini",
"name": "Phi 3.5 Mini",
"category": "AI Models",
"is_open_source": true,
"website": "https://azure.microsoft.com/en-us/products/phi",
"description": "Latest lightweight powerhouse from Microsoft, beating many larger models.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Phi",
"AI",
"LLM",
"Microsoft"
],
"hardware_req": "3GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 128000,
"parameters_total_b": 3.8,
"parameters_active_b": 3.8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/phi.svg"
},
{
"slug": "phi-3-5-moe",
"name": "Phi 3.5 MoE",
"category": "AI Models",
"is_open_source": true,
"website": "https://azure.microsoft.com/en-us/products/phi",
"description": "Mixture-of-Experts model combining 16x3.8B experts.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Phi",
"AI",
"LLM",
"Microsoft"
],
"hardware_req": "29GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 29,
"context_window_tokens": 128000,
"parameters_total_b": 42,
"parameters_active_b": 42,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/phi.svg"
},
{
"slug": "phi-3-5-vision",
"name": "Phi 3.5 Vision",
"category": "AI Models",
"is_open_source": true,
"website": "https://azure.microsoft.com/en-us/products/phi",
"description": "Multimodal version of Phi 3.5 capable of image analysis.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Phi",
"AI",
"LLM",
"Microsoft"
],
"hardware_req": "3GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 128000,
"parameters_total_b": 4.2,
"parameters_active_b": 4.2,
"is_multimodal": true
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/phi.svg"
},
{
"slug": "phi-3-mini",
"name": "Phi 3 Mini",
"category": "AI Models",
"is_open_source": true,
"website": "https://azure.microsoft.com/en-us/products/phi",
"description": "Highly capable 3.8B model trained on textbook data.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Phi",
"AI",
"LLM",
"Microsoft"
],
"hardware_req": "3GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 128000,
"parameters_total_b": 3.8,
"parameters_active_b": 3.8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/phi.svg"
},
{
"slug": "phi-3-medium",
"name": "Phi 3 Medium",
"category": "AI Models",
"is_open_source": true,
"website": "https://azure.microsoft.com/en-us/products/phi",
"description": "14B parameter version of the Phi-3 family.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Phi",
"AI",
"LLM",
"Microsoft"
],
"hardware_req": "10GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 128000,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/phi.svg"
},
{
"slug": "orca-2-13b",
"name": "Orca 2 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://azure.microsoft.com/en-us/products/phi",
"description": "Microsoft's research model exploring reasoning capabilities.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Phi",
"AI",
"LLM",
"Microsoft"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "yi-1-5-6b",
"name": "Yi 1.5 6B",
"category": "AI Models",
"is_open_source": true,
"website": "https://01.ai",
"description": "Strong 6B model from 01.AI.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"01.AI",
"Yi"
],
"hardware_req": "4GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "yi-1-5-9b",
"name": "Yi 1.5 9B",
"category": "AI Models",
"is_open_source": true,
"website": "https://01.ai",
"description": "9B parameter model optimized for coding and math.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"01.AI",
"Yi"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 9,
"parameters_active_b": 9,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "yi-1-5-34b",
"name": "Yi 1.5 34B",
"category": "AI Models",
"is_open_source": true,
"website": "https://01.ai",
"description": "Highly rated 34B model, popular in the community.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"01.AI",
"Yi"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 4096,
"parameters_total_b": 34,
"parameters_active_b": 34,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "yi-large",
"name": "Yi Large",
"category": "AI Models",
"is_open_source": true,
"website": "https://01.ai",
"description": "Proprietary-class open weights model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"01.AI",
"Yi"
],
"hardware_req": "70GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 70,
"context_window_tokens": 32000,
"parameters_total_b": 100,
"parameters_active_b": 100,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "command-r",
"name": "Command R",
"category": "AI Models",
"is_open_source": true,
"website": "https://cohere.com",
"description": "Optimized for RAG (Retrieval Augmented Generation) and tool use.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Cohere For AI",
"Cohere",
"LLM",
"RAG",
"AI"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 128000,
"parameters_total_b": 35,
"parameters_active_b": 35,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "command-r-plus",
"name": "Command R+",
"category": "AI Models",
"is_open_source": true,
"website": "https://cohere.com",
"description": "Massive RAG-optimized model with advanced reasoning.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Cohere For AI",
"Cohere",
"LLM",
"RAG",
"AI"
],
"hardware_req": "73GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 73,
"context_window_tokens": 128000,
"parameters_total_b": 104,
"parameters_active_b": 104,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "dolphin-2-9-llama-3-8b",
"name": "Dolphin 2.9 Llama 3 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://erichartford.com",
"description": "Uncensored fine-tune of Llama 3 8B.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Roleplay",
"Uncensored",
"LLM",
"Cognitive Computations",
"AI"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 8192,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "dolphin-2-9-2-qwen-2-72b",
"name": "Dolphin 2.9.2 Qwen 2 72B",
"category": "AI Models",
"is_open_source": true,
"website": "https://erichartford.com",
"description": "Powerful uncensored chat model based on Qwen 2.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Roleplay",
"Uncensored",
"LLM",
"Cognitive Computations",
"AI"
],
"hardware_req": "50GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 50,
"context_window_tokens": 32000,
"parameters_total_b": 72,
"parameters_active_b": 72,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "dolphin-mixtral-8x7b",
"name": "Dolphin Mixtral 8x7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://erichartford.com",
"description": "One of the most popular uncensored MoE models.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Roleplay",
"Uncensored",
"LLM",
"Cognitive Computations",
"AI"
],
"hardware_req": "33GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 33,
"context_window_tokens": 32000,
"parameters_total_b": 47,
"parameters_active_b": 47,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "hermes-3-llama-3-1-8b",
"name": "Hermes 3 Llama 3.1 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://nousresearch.com",
"description": "Unlock the full potential of Llama 3.1 with advanced agentic capabilities.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Fine-tune",
"AI",
"LLM",
"Nous Research"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 128000,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "hermes-3-llama-3-1-70b",
"name": "Hermes 3 Llama 3.1 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://nousresearch.com",
"description": "70B version of the Hermes 3 agentic fine-tune.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Fine-tune",
"AI",
"LLM",
"Nous Research"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 128000,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "nous-hermes-2-mixtral-8x7b",
"name": "Nous Hermes 2 Mixtral 8x7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://nousresearch.com",
"description": "High-quality instruction tuned Mixtral.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Fine-tune",
"AI",
"LLM",
"Nous Research"
],
"hardware_req": "33GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 33,
"context_window_tokens": 32000,
"parameters_total_b": 47,
"parameters_active_b": 47,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "solar-10-7b",
"name": "Solar 10.7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://upstage.ai",
"description": "Innovative 10.7B model created using depth up-scaling of Llama 2.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Upstage",
"Solar",
"LLM",
"Depth Upscaling",
"AI"
],
"hardware_req": "7GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 7,
"context_window_tokens": 4096,
"parameters_total_b": 10.7,
"parameters_active_b": 10.7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "solar-pro",
"name": "Solar Pro",
"category": "AI Models",
"is_open_source": true,
"website": "https://upstage.ai",
"description": "Advanced scale-up of the Solar architecture.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Upstage",
"Solar",
"LLM",
"Depth Upscaling",
"AI"
],
"hardware_req": "15GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 15,
"context_window_tokens": 4096,
"parameters_total_b": 22,
"parameters_active_b": 22,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek-coder-v2-16b",
"name": "DeepSeek Coder V2 16B",
"category": "AI Models",
"is_open_source": true,
"website": "https://deepseek.com",
"description": "Powerful coding-specific MoE model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Coding",
"AI",
"LLM",
"DeepSeek"
],
"hardware_req": "11GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 11,
"context_window_tokens": 128000,
"parameters_total_b": 16,
"parameters_active_b": 16,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek-coder-v2-236b",
"name": "DeepSeek Coder V2 236B",
"category": "AI Models",
"is_open_source": true,
"website": "https://deepseek.com",
"description": "Massive coding model rivaling GPT-4 across benchmarks.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Coding",
"AI",
"LLM",
"DeepSeek"
],
"hardware_req": "165GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 165,
"context_window_tokens": 128000,
"parameters_total_b": 236,
"parameters_active_b": 236,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek-llm-7b",
"name": "DeepSeek LLM 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://deepseek.com",
"description": "General purpose 7B chat model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Coding",
"AI",
"LLM",
"DeepSeek"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 32000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek-llm-67b",
"name": "DeepSeek LLM 67B",
"category": "AI Models",
"is_open_source": true,
"website": "https://deepseek.com",
"description": "Large general purpose model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Coding",
"AI",
"LLM",
"DeepSeek"
],
"hardware_req": "47GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 47,
"context_window_tokens": 32000,
"parameters_total_b": 67,
"parameters_active_b": 67,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "stable-lm-2-1-6b",
"name": "Stable LM 2 1.6B",
"category": "AI Models",
"is_open_source": true,
"website": "https://stability.ai",
"description": "Very small, efficient model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Stability AI",
"AI",
"LLM"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1.6,
"parameters_active_b": 1.6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "stable-lm-2-12b",
"name": "Stable LM 2 12B",
"category": "AI Models",
"is_open_source": true,
"website": "https://stability.ai",
"description": "Balanced 12B model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Stability AI",
"AI",
"LLM"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 4096,
"parameters_total_b": 12,
"parameters_active_b": 12,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "stable-code-3b",
"name": "Stable Code 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://stability.ai",
"description": "Specialized 3B coding model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Stability AI",
"AI",
"LLM"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 16384,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "starling-lm-7b-alpha",
"name": "Starling LM 7B Alpha",
"category": "AI Models",
"is_open_source": true,
"website": "https://nexusflow.ai",
"description": "RLHF fine-tune known for high quality responses.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Nexusflow",
"RLHF"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 8192,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "starling-lm-7b-beta",
"name": "Starling LM 7B Beta",
"category": "AI Models",
"is_open_source": true,
"website": "https://nexusflow.ai",
"description": "Improved beta version of the Starling RLHF model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Nexusflow",
"RLHF"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 8192,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "openchat-3-5",
"name": "OpenChat 3.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://openchat.team",
"description": "Fine-tuned Mistral 7B using C-RLFT strategy.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"C-RLFT",
"AI",
"LLM",
"OpenChat"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 8192,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "openchat-3-6",
"name": "OpenChat 3.6",
"category": "AI Models",
"is_open_source": true,
"website": "https://openchat.team",
"description": "Updated version based on Llama 3 8B.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"C-RLFT",
"AI",
"LLM",
"OpenChat"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 8192,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "tinyllama-1-1b",
"name": "TinyLlama 1.1B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/jzhang38/TinyLlama",
"description": "The most popular ~1B model, trained on 3T tokens.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Small",
"AI",
"LLM",
"TinyLlama"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 2048,
"parameters_total_b": 1.1,
"parameters_active_b": 1.1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/meta.svg"
},
{
"slug": "falcon-2-11b",
"name": "Falcon 2 11B",
"category": "AI Models",
"is_open_source": true,
"website": "https://falconllm.tii.ae",
"description": "TII's efficient 11B model with strong reasoning capabilities.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Falcon",
"LLM",
"AI",
"TII"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 2048,
"parameters_total_b": 11,
"parameters_active_b": 11,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/falcon.svg"
},
{
"slug": "falcon-180b",
"name": "Falcon 180B",
"category": "AI Models",
"is_open_source": true,
"website": "https://falconllm.tii.ae",
"description": "Massive open model, one of the largest available.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Falcon",
"LLM",
"AI",
"TII"
],
"hardware_req": "126GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 126,
"context_window_tokens": 2048,
"parameters_total_b": 180,
"parameters_active_b": 180,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/falcon.svg"
},
{
"slug": "falcon-40b",
"name": "Falcon 40B",
"category": "AI Models",
"is_open_source": true,
"website": "https://falconllm.tii.ae",
"description": "The original high-performance open model form TII.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Falcon",
"LLM",
"AI",
"TII"
],
"hardware_req": "28GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 28,
"context_window_tokens": 2048,
"parameters_total_b": 40,
"parameters_active_b": 40,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/falcon.svg"
},
{
"slug": "falcon-7b",
"name": "Falcon 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://falconllm.tii.ae",
"description": "Smaller variant of the Falcon family.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Falcon",
"LLM",
"AI",
"TII"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 2048,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/falcon.svg"
},
{
"slug": "glm-4-9b",
"name": "GLM 4 9B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/THUDM/GLM-4",
"description": "Powerful multilingual model from Zhipu AI.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"GLM",
"Zhipu AI",
"LLM",
"AI"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 128000,
"parameters_total_b": 9,
"parameters_active_b": 9,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "chatglm3-6b",
"name": "ChatGLM3 6B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/THUDM/GLM-4",
"description": "Optimized Chinese-English conversational model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"GLM",
"Zhipu AI",
"LLM",
"AI"
],
"hardware_req": "4GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 32000,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "granite-3-0-8b-instruct",
"name": "Granite 3.0 8B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.ibm.com/granite",
"description": "IBM's enterprise-grade open model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"IBM",
"LLM",
"AI",
"Enterprise"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "granite-3-0-2b-instruct",
"name": "Granite 3.0 2B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.ibm.com/granite",
"description": "Efficient enterprise model for lower resource environments.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"IBM",
"LLM",
"AI",
"Enterprise"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "granite-code-3b",
"name": "Granite Code 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.ibm.com/granite",
"description": "IBM specialized code model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"IBM",
"LLM",
"AI",
"Enterprise"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "granite-code-8b",
"name": "Granite Code 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.ibm.com/granite",
"description": "Larger coding model from IBM.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"IBM",
"LLM",
"AI",
"Enterprise"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "flux-1-schnell",
"name": "Flux.1 Schnell",
"category": "AI Models",
"is_open_source": true,
"website": "https://blackforestlabs.ai",
"description": "Fastest state-of-the-art open image generation model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Black Forest Labs",
"Image Generation",
"AI",
"Diffusion"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 77,
"parameters_total_b": 12,
"parameters_active_b": 12,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/flux.svg"
},
{
"slug": "flux-1-dev",
"name": "Flux.1 Dev",
"category": "AI Models",
"is_open_source": true,
"website": "https://blackforestlabs.ai",
"description": "Developer version of the powerful Flux image model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Black Forest Labs",
"Image Generation",
"AI",
"Diffusion"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 77,
"parameters_total_b": 12,
"parameters_active_b": 12,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/flux.svg"
},
{
"slug": "sdxl-1-0",
"name": "SDXL 1.0",
"category": "AI Models",
"is_open_source": true,
"website": "https://stability.ai",
"description": "The benchmark for open source image generation.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Image Generation",
"AI",
"Diffusion",
"Stability AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 77,
"parameters_total_b": 6.6,
"parameters_active_b": 6.6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "sd-3-medium",
"name": "SD 3 Medium",
"category": "AI Models",
"is_open_source": true,
"website": "https://stability.ai",
"description": "Stability AI's latest medium-sized image model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Image Generation",
"AI",
"Diffusion",
"Stability AI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 77,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "stable-cascade",
"name": "Stable Cascade",
"category": "AI Models",
"is_open_source": true,
"website": "https://stability.ai",
"description": "Efficient cascade architecture for high detail images.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Image Generation",
"AI",
"Diffusion",
"Stability AI"
],
"hardware_req": "3GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 77,
"parameters_total_b": 3.6,
"parameters_active_b": 3.6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "internlm-2-5-7b",
"name": "InternLM 2.5 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://internlm.intern-ai.org.cn",
"description": "High performance 7B model with strong reasoning.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Shanghai AI Lab",
"LLM",
"AI",
"InternLM"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 32000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "internlm-2-5-20b",
"name": "InternLM 2.5 20B",
"category": "AI Models",
"is_open_source": true,
"website": "https://internlm.intern-ai.org.cn",
"description": "Balanced 20B model filling the gap between 7B and 70B.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Shanghai AI Lab",
"LLM",
"AI",
"InternLM"
],
"hardware_req": "14GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 14,
"context_window_tokens": 32000,
"parameters_total_b": 20,
"parameters_active_b": 20,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "baichuan-2-7b",
"name": "Baichuan 2 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.baichuan-ai.com",
"description": "Top tier Chinese-English bilingual model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Baichuan",
"LLM",
"AI",
"Baichuan Inc."
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "baichuan-2-13b",
"name": "Baichuan 2 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.baichuan-ai.com",
"description": "Larger variant of the popular Baichuan series.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Baichuan",
"LLM",
"AI",
"Baichuan Inc."
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "minicpm-2-4b",
"name": "MiniCPM 2.4B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/OpenBMB/MiniCPM",
"description": "High efficiency edge model optimization.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"OpenBMB",
"Mobile",
"LLM",
"Edge",
"AI"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 2.4,
"parameters_active_b": 2.4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "minicpm-v-2-6",
"name": "MiniCPM V 2.6",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/OpenBMB/MiniCPM",
"description": "Powerful multimodal model for mobile devices.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"OpenBMB",
"Mobile",
"LLM",
"Edge",
"AI"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "exaone-3-0-7-8b",
"name": "Exaone 3.0 7.8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.lgresearch.ai",
"description": "LG's competitive open model entry.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LG",
"LG AI Research",
"LLM",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7.8,
"parameters_active_b": 7.8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "jamba-v0-1",
"name": "Jamba v0.1",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.ai21.com/jamba",
"description": "First production-grade Mamba-Transformer hybrid model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Hybrid",
"LLM",
"AI",
"Mamba",
"AI21 Labs"
],
"hardware_req": "36GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 36,
"context_window_tokens": 256000,
"parameters_total_b": 52,
"parameters_active_b": 52,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "grok-1",
"name": "Grok 1",
"category": "AI Models",
"is_open_source": true,
"website": "https://x.ai",
"description": "Massive 314B parameter open weights model from xAI.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Grok",
"LLM",
"AI",
"xAI"
],
"hardware_req": "220GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 220,
"context_window_tokens": 8192,
"parameters_total_b": 314,
"parameters_active_b": 314,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/grok.svg"
},
{
"slug": "deepseek-vl-7b",
"name": "DeepSeek VL 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://deepseek.com",
"description": "Vision language model from DeepSeek.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"DeepSeek",
"Vision",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": true
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "deepseek-vl-1-3b",
"name": "DeepSeek VL 1.3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://deepseek.com",
"description": "Small vision language model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"DeepSeek",
"Vision",
"AI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1.3,
"parameters_active_b": 1.3,
"is_multimodal": true
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "whisper-large-v3",
"name": "Whisper Large v3",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/openai/whisper",
"description": "State-of-the-art automatic speech recognition model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"ASR",
"Audio",
"OpenAI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 0,
"parameters_total_b": 1.5,
"parameters_active_b": 1.5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "whisper-medium",
"name": "Whisper Key",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/openai/whisper",
"description": "Balanced speech recognition model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"ASR",
"Audio",
"OpenAI"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 0,
"parameters_total_b": 0.7,
"parameters_active_b": 0.7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "seamless-m4t-large",
"name": "Seamless M4T Large",
"category": "AI Models",
"is_open_source": true,
"website": "https://ai.meta.com/research/seamless-communication/",
"description": "Massive multilingual translation and transcription model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"Meta",
"Audio",
"Translation"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 0,
"parameters_total_b": 2.3,
"parameters_active_b": 2.3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "starcoder-2-15b",
"name": "StarCoder 2 15B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/bigcode",
"description": "The successor to the original StarCoder, trained on The Stack v2.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"ServiceNow",
"BigCode",
"AI",
"Coding"
],
"hardware_req": "10GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 16384,
"parameters_total_b": 15,
"parameters_active_b": 15,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "starcoder-2-7b",
"name": "StarCoder 2 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/bigcode",
"description": "Mid-sized coding model from the BigCode project.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"ServiceNow",
"BigCode",
"AI",
"Coding"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 16384,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "starcoder-2-3b",
"name": "StarCoder 2 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/bigcode",
"description": "Efficient coding assistant.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"ServiceNow",
"BigCode",
"AI",
"Coding"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 16384,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "llava-1-6-34b",
"name": "LLaVA 1.6 34B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llava-vl.github.io",
"description": "High performance large multimodal model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multimodal",
"Vision",
"LLaVA Team",
"AI"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 4096,
"parameters_total_b": 34,
"parameters_active_b": 34,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "llava-1-6-13b",
"name": "LLaVA 1.6 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llava-vl.github.io",
"description": "Improved visual reasoning capabilities.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multimodal",
"Vision",
"LLaVA Team",
"AI"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "llava-1-6-7b",
"name": "LLaVA 1.6 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://llava-vl.github.io",
"description": "Efficient multimodal model base on Vicuna.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multimodal",
"Vision",
"LLaVA Team",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "bakllava",
"name": "BakLLaVA",
"category": "AI Models",
"is_open_source": true,
"website": "https://llava-vl.github.io",
"description": "Mistral-based LLaVA variant.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multimodal",
"Vision",
"LLaVA Team",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "bloom-176b",
"name": "BLOOM 176B",
"category": "AI Models",
"is_open_source": true,
"website": "https://bigscience.huggingface.co",
"description": "The world's largest open-multilingual language model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multilingual",
"Open Science",
"BigScience",
"AI"
],
"hardware_req": "123GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 123,
"context_window_tokens": 2048,
"parameters_total_b": 176,
"parameters_active_b": 176,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "bloomz-176b",
"name": "BLOOMZ 176B",
"category": "AI Models",
"is_open_source": true,
"website": "https://bigscience.huggingface.co",
"description": "Instruction tuned version of BLOOM.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multilingual",
"Open Science",
"BigScience",
"AI"
],
"hardware_req": "123GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 123,
"context_window_tokens": 2048,
"parameters_total_b": 176,
"parameters_active_b": 176,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "bloom-7b",
"name": "BLOOM 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://bigscience.huggingface.co",
"description": "Smaller variant of the BLOOM family.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multilingual",
"Open Science",
"BigScience",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 2048,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "pythia-12b",
"name": "Pythia 12B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/EleutherAI/pythia",
"description": "Designed to interpret and analyze LLM training dynamics.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Research",
"EleutherAI",
"AI"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 2048,
"parameters_total_b": 12,
"parameters_active_b": 12,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "pythia-6-9b",
"name": "Pythia 6.9B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/EleutherAI/pythia",
"description": "Standard research model size.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Research",
"EleutherAI",
"AI"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 2048,
"parameters_total_b": 6.9,
"parameters_active_b": 6.9,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "opt-175b",
"name": "OPT 175B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/facebookresearch/metaseq",
"description": "Meta's Open Pre-trained Transformer, matching GPT-3 performance.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Legacy",
"Meta"
],
"hardware_req": "122GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 122,
"context_window_tokens": 2048,
"parameters_total_b": 175,
"parameters_active_b": 175,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "opt-66b",
"name": "OPT 66B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/facebookresearch/metaseq",
"description": "Large scale OPT model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Legacy",
"Meta"
],
"hardware_req": "46GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 46,
"context_window_tokens": 2048,
"parameters_total_b": 66,
"parameters_active_b": 66,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "opt-30b",
"name": "OPT 30B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/facebookresearch/metaseq",
"description": "Mid-range OPT model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Legacy",
"Meta"
],
"hardware_req": "21GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 2048,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "h2o-danube-2-1-8b",
"name": "H2O Danube 2 1.8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://h2o.ai",
"description": "Highly efficient mobile-class model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"H2O",
"AI",
"H2O.ai"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 8192,
"parameters_total_b": 1.8,
"parameters_active_b": 1.8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "fuyu-8b",
"name": "Fuyu 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://adept.ai",
"description": "Simple architecture multimodal model for digital agents.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Multimodal",
"Adept",
"Agent",
"AI"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 8192,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "nexusraven-v2-13b",
"name": "NexusRaven V2 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://nexusflow.ai",
"description": "Specialized in function calling and tool use.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Nexusflow",
"Raven"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "xverse-65b",
"name": "Xverse 65B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/xverse-ai",
"description": "Large multilingual model trained from scratch.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Shenzhen Yuanxiang",
"Multilingual"
],
"hardware_req": "46GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 46,
"context_window_tokens": 4096,
"parameters_total_b": 65,
"parameters_active_b": 65,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "xverse-13b",
"name": "Xverse 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/xverse-ai",
"description": "Efficient multilingual model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Shenzhen Yuanxiang",
"Multilingual"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "aquila2-34b",
"name": "Aquila2 34B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/FlagAI-Open/FlagAI",
"description": "Strong performance on reasoning benchmarks.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"BAAI",
"AI"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 4096,
"parameters_total_b": 34,
"parameters_active_b": 34,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "telechat-12b",
"name": "TeleChat 12B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/Tele-AI/Telechat",
"description": "Telecommunications oriented LLM.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Telecom",
"China Telecom",
"AI"
],
"hardware_req": "8GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 8,
"context_window_tokens": 4096,
"parameters_total_b": 12,
"parameters_active_b": 12,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "orion-14b",
"name": "Orion 14B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/OrionStarAI/Orion",
"description": "Chat and conversational model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Orion",
"AI",
"OrionStar"
],
"hardware_req": "10GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "seallm-7b-v2-5",
"name": "SeaLLM 7B v2.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/SeaLLMs",
"description": "State-of-the-art multilingual LLM for Southeast Asian languages.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Southeast Asia",
"AI",
"Alibaba (sea-lion)"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "openbiollm-8b",
"name": "OpenBioLLM 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/saama",
"description": "Advanced medical LLM outperforming GPT-4 on biomedical benchmarks.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Saama AI",
"AI",
"LLM",
"Medical",
"Biology"
],
"hardware_req": "6GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "openbiollm-70b",
"name": "OpenBioLLM 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/saama",
"description": "Massive scale biomedical research model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Saama AI",
"AI",
"LLM",
"Medical",
"Biology"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "meditron-70b",
"name": "Meditron 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/epfl-llm",
"description": "Open-access LLM adapted to the medical domain.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"EPFL",
"AI",
"Medical"
],
"hardware_req": "49GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "meditron-7b",
"name": "Meditron 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/epfl-llm",
"description": "Efficient medical assistant model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"EPFL",
"AI",
"Medical"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "gorilla-openfunctions-v2",
"name": "Gorilla OpenFunctions v2",
"category": "AI Models",
"is_open_source": true,
"website": "https://gorilla.cs.berkeley.edu",
"description": "The best open source model for API function calling.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"AI",
"LLM",
"Agents",
"Berkeley",
"API"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "wizardlm-2-8x22b",
"name": "WizardLM 2 8x22B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/nlpxucan/WizardLM",
"description": "Top-tier reasoning model from Microsoft using Evol-Instruct.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Microsoft",
"AI",
"Evol-Instruct"
],
"hardware_req": "99GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 99,
"context_window_tokens": 65536,
"parameters_total_b": 141,
"parameters_active_b": 141,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "wizardlm-2-7b",
"name": "WizardLM 2 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/nlpxucan/WizardLM",
"description": "Fastest and most capable 7B model for complex instructions.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Microsoft",
"AI",
"Evol-Instruct"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 32000,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "vicuna-13b-v1-5",
"name": "Vicuna 13B v1.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://lmsys.org",
"description": "The classic open chat model based on Llama 2.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"LMSYS",
"Chatbot"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 16384,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "vicuna-7b-v1-5",
"name": "Vicuna 7B v1.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://lmsys.org",
"description": "Highly efficient chat model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"LMSYS",
"Chatbot"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 16384,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "zephyr-7b-beta",
"name": "Zephyr 7B Beta",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/HuggingFaceH4",
"description": "Pioneered DPO (Direct Preference Optimization) for better alignment without RLHF.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Hugging Face H4",
"DPO"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 8192,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "zephyr-141b-a39b",
"name": "Zephyr 141B A39B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/HuggingFaceH4",
"description": "Experimental DPO fine-tune of Mixtral 8x22B.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"Hugging Face H4",
"DPO"
],
"hardware_req": "99GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 99,
"context_window_tokens": 4096,
"parameters_total_b": 141,
"parameters_active_b": 141,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "openelm-3b",
"name": "OpenELM 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/apple/corenet",
"description": "Apple's efficiently layered open model for devices.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"On-Device",
"Apple"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 2048,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "openelm-1-1b",
"name": "OpenELM 1.1B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/apple/corenet",
"description": "Tiny Apple model for extreme edge cases.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"On-Device",
"Apple"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 2048,
"parameters_total_b": 1.1,
"parameters_active_b": 1.1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mamba-2-8b",
"name": "Mamba 2.8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/state-spaces/mamba",
"description": "Linear-time sequence modeling with state space architecture.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Cartesia",
"AI",
"SSM",
"LLM",
"Non-Transformer"
],
"hardware_req": "2GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 0,
"parameters_total_b": 2.8,
"parameters_active_b": 2.8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "mamba-1-4b",
"name": "Mamba 1.4B",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/state-spaces/mamba",
"description": "Efficient non-transformer architecture.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Cartesia",
"AI",
"SSM",
"LLM",
"Non-Transformer"
],
"hardware_req": "1GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 0,
"parameters_total_b": 1.4,
"parameters_active_b": 1.4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "rwkv-6-14b",
"name": "RWKV 6 14B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.rwkv.com",
"description": "RNN with Transformer-level performance and infinite context potential.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"RNN",
"BlinkDL"
],
"hardware_req": "10GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 0,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "rwkv-6-7b",
"name": "RWKV 6 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.rwkv.com",
"description": "Efficient RNN language model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"AI",
"RNN",
"BlinkDL"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 0,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "cerebras-gpt-13b",
"name": "Cerebras GPT 13B",
"category": "AI Models",
"is_open_source": true,
"website": "https://www.cerebras.net",
"description": "Trained on the massive CS-2 wafer-scale engine.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"LLM",
"Cerebras",
"AI",
"Wafer-Scale"
],
"hardware_req": "9GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 2048,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361"
},
{
"slug": "qwen-audio-chat",
"name": "Qwen-Audio-Chat",
"category": "AI Models",
"is_open_source": true,
"website": "https://github.com/QwenLM/Qwen-Audio",
"description": "Universal audio understanding model.",
"pros": [
"Open Source",
"High Performance",
"Run Locally"
],
"cons": [
"Requires GPU inference",
"Management complexity"
],
"stars": 0,
"language": "Python",
"license": "Open Weights",
"tags": [
"Audio",
"AI",
"Multimodal",
"Alibaba Cloud"
],
"hardware_req": "5GB+ VRAM",
"hosting_type": "both",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 0,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-7b-instruct",
"name": "Qwen2.5 7B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct",
"description": "Open source model Qwen/Qwen2.5-7B-Instruct. 1073 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1073,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-7B",
"base_model:finetune:Qwen/Qwen2.5-7B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-7b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-0.6b",
"name": "Qwen3 0.6B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-0.6B",
"description": "Open source model Qwen/Qwen3-0.6B. 1083 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1083,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-0.6B-Base",
"base_model:finetune:Qwen/Qwen3-0.6B-Base",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-0.6b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "gpt2",
"name": "Gpt2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/openai-community/gpt2",
"description": "Open source model openai-community/gpt2. 3114 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3114,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"tflite",
"rust",
"onnx",
"safetensors",
"gpt2",
"exbert",
"en",
"doi:10.57967/hf/0039",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt2"
},
{
"slug": "qwen2.5-1.5b-instruct",
"name": "Qwen2.5 1.5B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct",
"description": "Open source model Qwen/Qwen2.5-1.5B-Instruct. 617 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 617,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-1.5B",
"base_model:finetune:Qwen/Qwen2.5-1.5B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-1.5b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-3b-instruct",
"name": "Qwen2.5 3B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-3B-Instruct",
"description": "Open source model Qwen/Qwen2.5-3B-Instruct. 404 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 404,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-3B",
"base_model:finetune:Qwen/Qwen2.5-3B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-3b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "llama-3.1-8b-instruct",
"name": "Llama 3.1 8B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct",
"description": "Open source model meta-llama/Llama-3.1-8B-Instruct. 5467 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 5467,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-3.1-8B",
"base_model:finetune:meta-llama/Llama-3.1-8B",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.1-8b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "gpt-oss-20b",
"name": "Gpt Oss 20B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/openai/gpt-oss-20b",
"description": "Open source model openai/gpt-oss-20b. 4378 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4378,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gpt_oss",
"vllm",
"conversational",
"arxiv:2508.10925",
"endpoints_compatible",
"8-bit",
"mxfp4",
"deploy:azure",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 14,
"context_window_tokens": 4096,
"parameters_total_b": 20,
"parameters_active_b": 20,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt-oss-20b"
},
{
"slug": "qwen2.5-0.5b-instruct",
"name": "Qwen2.5 0.5B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct",
"description": "Open source model Qwen/Qwen2.5-0.5B-Instruct. 463 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 463,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-0.5B",
"base_model:finetune:Qwen/Qwen2.5-0.5B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-0.5b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-4b",
"name": "Qwen3 4B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-4B",
"description": "Open source model Qwen/Qwen3-4B. 552 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 552,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-4B-Base",
"base_model:finetune:Qwen/Qwen3-4B-Base",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-4b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-8b",
"name": "Qwen3 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-8B",
"description": "Open source model Qwen/Qwen3-8B. 940 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 940,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-8B-Base",
"base_model:finetune:Qwen/Qwen3-8B-Base",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-8b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-32b-instruct",
"name": "Qwen2.5 32B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-32B-Instruct",
"description": "Open source model Qwen/Qwen2.5-32B-Instruct. 328 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 328,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-32B",
"base_model:finetune:Qwen/Qwen2.5-32B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-32b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "opt-125m",
"name": "Opt 125M",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/facebook/opt-125m",
"description": "Open source model facebook/opt-125m. 233 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 233,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"opt",
"en",
"arxiv:2205.01068",
"arxiv:2005.14165",
"text-generation-inference",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "opt-125m"
},
{
"slug": "qwen3-1.7b",
"name": "Qwen3 1.7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-1.7B",
"description": "Open source model Qwen/Qwen3-1.7B. 422 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 422,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-1.7B-Base",
"base_model:finetune:Qwen/Qwen3-1.7B-Base",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-1.7b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "tiny-qwen2forcausallm-2.5",
"name": "Tiny Qwen2Forcausallm 2.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/trl-internal-testing/tiny-Qwen2ForCausalLM-2.5",
"description": "Open source model trl-internal-testing/tiny-Qwen2ForCausalLM-2.5. 3 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"trl",
"conversational",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tiny-qwen2forcausallm-2.5",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "dolphin-2.9.1-yi-1.5-34b",
"name": "Dolphin 2.9.1 Yi 1.5 34B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/dphn/dolphin-2.9.1-yi-1.5-34b",
"description": "Open source model dphn/dolphin-2.9.1-yi-1.5-34b. 54 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 54,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"generated_from_trainer",
"axolotl",
"conversational",
"dataset:cognitivecomputations/Dolphin-2.9",
"dataset:teknium/OpenHermes-2.5",
"dataset:m-a-p/CodeFeedback-Filtered-Instruction",
"dataset:cognitivecomputations/dolphin-coder",
"dataset:cognitivecomputations/samantha-data",
"dataset:microsoft/orca-math-word-problems-200k",
"dataset:Locutusque/function-calling-chatml",
"dataset:internlm/Agent-FLAN",
"base_model:01-ai/Yi-1.5-34B",
"base_model:finetune:01-ai/Yi-1.5-34B",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 24,
"context_window_tokens": 4096,
"parameters_total_b": 34,
"parameters_active_b": 34,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "dolphin-2.9.1-yi-1.5-34b"
},
{
"slug": "qwen3-embedding-0.6b",
"name": "Qwen3 Embedding 0.6B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Embedding-0.6B",
"description": "Open source model Qwen/Qwen3-Embedding-0.6B. 879 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 879,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"sentence-transformers",
"safetensors",
"qwen3",
"transformers",
"sentence-similarity",
"feature-extraction",
"text-embeddings-inference",
"arxiv:2506.05176",
"base_model:Qwen/Qwen3-0.6B-Base",
"base_model:finetune:Qwen/Qwen3-0.6B-Base",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-embedding-0.6b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "gpt-oss-120b",
"name": "Gpt Oss 120B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/openai/gpt-oss-120b",
"description": "Open source model openai/gpt-oss-120b. 4503 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4503,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gpt_oss",
"vllm",
"conversational",
"arxiv:2508.10925",
"endpoints_compatible",
"8-bit",
"mxfp4",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 84,
"context_window_tokens": 4096,
"parameters_total_b": 120,
"parameters_active_b": 120,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt-oss-120b"
},
{
"slug": "qwen3-4b-instruct-2507",
"name": "Qwen3 4B Instruct 2507",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507",
"description": "Open source model Qwen/Qwen3-4B-Instruct-2507. 730 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 730,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-4b-instruct-2507",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "moondream2",
"name": "Moondream2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/vikhyatk/moondream2",
"description": "Open source model vikhyatk/moondream2. 1373 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1373,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"moondream1",
"image-text-to-text",
"custom_code",
"doi:10.57967/hf/6762",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "moondream2"
},
{
"slug": "llama-3.2-1b-instruct",
"name": "Llama 3.2 1B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct",
"description": "Open source model meta-llama/Llama-3.2-1B-Instruct. 1292 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1292,
"language": "Python",
"license": "llama3.2",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-1b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen2-1.5b-instruct",
"name": "Qwen2 1.5B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2-1.5B-Instruct",
"description": "Open source model Qwen/Qwen2-1.5B-Instruct. 158 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 158,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2-1.5b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-coder-0.5b-instruct",
"name": "Qwen2.5 Coder 0.5B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct",
"description": "Open source model Qwen/Qwen2.5-Coder-0.5B-Instruct. 64 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 64,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-0.5B",
"base_model:finetune:Qwen/Qwen2.5-Coder-0.5B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-0.5b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "kimi-k2.5",
"name": "Kimi K2.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/mlx-community/Kimi-K2.5",
"description": "Open source model mlx-community/Kimi-K2.5. 28 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 28,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"mlx",
"safetensors",
"kimi_k25",
"conversational",
"custom_code",
"base_model:moonshotai/Kimi-K2.5",
"base_model:quantized:moonshotai/Kimi-K2.5",
"4-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "kimi-k2.5"
},
{
"slug": "mistral-7b-instruct-v0.2",
"name": "Mistral 7B Instruct V0.2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2",
"description": "Open source model mistralai/Mistral-7B-Instruct-v0.2. 3075 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3075,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"mistral",
"finetuned",
"mistral-common",
"conversational",
"arxiv:2310.06825",
"text-generation-inference",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "mistral-7b-instruct-v0.2",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "qwen3-30b-a3b-instruct-2507",
"name": "Qwen3 30B A3B Instruct 2507",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507",
"description": "Open source model Qwen/Qwen3-30B-A3B-Instruct-2507. 766 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 766,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2402.17463",
"arxiv:2407.02490",
"arxiv:2501.15383",
"arxiv:2404.06654",
"arxiv:2505.09388",
"eval-results",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-30b-a3b-instruct-2507",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "llm-jp-3-3.7b-instruct",
"name": "Llm Jp 3 3.7B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/llm-jp/llm-jp-3-3.7b-instruct",
"description": "Open source model llm-jp/llm-jp-3-3.7b-instruct. 13 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 13,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"en",
"ja",
"text-generation-inference",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llm-jp-3-3.7b-instruct"
},
{
"slug": "llama-3.2-3b-instruct",
"name": "Llama 3.2 3B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct",
"description": "Open source model meta-llama/Llama-3.2-3B-Instruct. 1986 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1986,
"language": "Python",
"license": "llama3.2",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-3b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "distilgpt2",
"name": "Distilgpt2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/distilbert/distilgpt2",
"description": "Open source model distilbert/distilgpt2. 609 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 609,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"tflite",
"rust",
"coreml",
"safetensors",
"gpt2",
"exbert",
"en",
"dataset:openwebtext",
"arxiv:1910.01108",
"arxiv:2201.08542",
"arxiv:2203.12574",
"arxiv:1910.09700",
"arxiv:1503.02531",
"model-index",
"co2_eq_emissions",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "distilgpt2"
},
{
"slug": "qwen3-embedding-8b",
"name": "Qwen3 Embedding 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Embedding-8B",
"description": "Open source model Qwen/Qwen3-Embedding-8B. 584 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 584,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"sentence-transformers",
"safetensors",
"qwen3",
"transformers",
"sentence-similarity",
"feature-extraction",
"text-embeddings-inference",
"arxiv:2506.05176",
"base_model:Qwen/Qwen3-8B-Base",
"base_model:finetune:Qwen/Qwen3-8B-Base",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-embedding-8b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "meta-llama-3-8b",
"name": "Meta Llama 3 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Meta-Llama-3-8B",
"description": "Open source model meta-llama/Meta-Llama-3-8B. 6458 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 6458,
"language": "Python",
"license": "llama3",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3-8b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "tinyllama-1.1b-chat-v1.0",
"name": "Tinyllama 1.1B Chat V1.0",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0",
"description": "Open source model TinyLlama/TinyLlama-1.1B-Chat-v1.0. 1526 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1526,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tinyllama-1.1b-chat-v1.0"
},
{
"slug": "glm-4.7-flash",
"name": "Glm 4.7 Flash",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/zai-org/GLM-4.7-Flash",
"description": "Open source model zai-org/GLM-4.7-Flash. 1538 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1538,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm4_moe_lite",
"conversational",
"en",
"zh",
"arxiv:2508.06471",
"eval-results",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.7-flash"
},
{
"slug": "llama-3.2-1b",
"name": "Llama 3.2 1B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.2-1B",
"description": "Open source model meta-llama/Llama-3.2-1B. 2295 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2295,
"language": "Python",
"license": "llama3.2",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-1b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-32b",
"name": "Qwen3 32B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-32B",
"description": "Open source model Qwen/Qwen3-32B. 656 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 656,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-32b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "llama-3.2-1b-instruct-fp8-dynamic",
"name": "Llama 3.2 1B Instruct Fp8 Dynamic",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/RedHatAI/Llama-3.2-1B-Instruct-FP8-dynamic",
"description": "Open source model RedHatAI/Llama-3.2-1B-Instruct-FP8-dynamic. 3 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3,
"language": "Python",
"license": "llama3.2",
"tags": [
"AI",
"LLM",
"safetensors",
"llama",
"fp8",
"vllm",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:quantized:meta-llama/Llama-3.2-1B-Instruct",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-1b-instruct-fp8-dynamic",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen2.5-coder-1.5b-instruct",
"name": "Qwen2.5 Coder 1.5B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct",
"description": "Open source model Qwen/Qwen2.5-Coder-1.5B-Instruct. 106 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 106,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-1.5B",
"base_model:finetune:Qwen/Qwen2.5-Coder-1.5B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-1.5b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "meta-llama-3-8b-instruct",
"name": "Meta Llama 3 8B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct",
"description": "Open source model meta-llama/Meta-Llama-3-8B-Instruct. 4380 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4380,
"language": "Python",
"license": "llama3",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3-8b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "gemma-3-1b-it",
"name": "Gemma 3 1B It",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/google/gemma-3-1b-it",
"description": "Open source model google/gemma-3-1b-it. 842 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 842,
"language": "Python",
"license": "gemma",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gemma3_text",
"conversational",
"arxiv:1905.07830",
"arxiv:1905.10044",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1705.03551",
"arxiv:1911.01547",
"arxiv:1907.10641",
"arxiv:1903.00161",
"arxiv:2009.03300",
"arxiv:2304.06364",
"arxiv:2103.03874",
"arxiv:2110.14168",
"arxiv:2311.12022",
"arxiv:2108.07732",
"arxiv:2107.03374",
"arxiv:2210.03057",
"arxiv:2106.03193",
"arxiv:1910.11856",
"arxiv:2502.12404",
"arxiv:2502.21228",
"arxiv:2404.16816",
"arxiv:2104.12756",
"arxiv:2311.16502",
"arxiv:2203.10244",
"arxiv:2404.12390",
"arxiv:1810.12440",
"arxiv:1908.02660",
"arxiv:2312.11805",
"base_model:google/gemma-3-1b-pt",
"base_model:finetune:google/gemma-3-1b-pt",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gemma-3-1b-it",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "phi-2",
"name": "Phi 2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/phi-2",
"description": "Open source model microsoft/phi-2. 3425 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3425,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi",
"nlp",
"code",
"en",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-2",
"logo_url": "/logos/phi.svg"
},
{
"slug": "qwen2.5-coder-7b-instruct",
"name": "Qwen2.5 Coder 7B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct",
"description": "Open source model Qwen/Qwen2.5-Coder-7B-Instruct. 646 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 646,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-7B",
"base_model:finetune:Qwen/Qwen2.5-Coder-7B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-7b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-7b",
"name": "Qwen2.5 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-7B",
"description": "Open source model Qwen/Qwen2.5-7B. 264 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 264,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"en",
"arxiv:2407.10671",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-7b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-r1-distill-qwen-1.5b",
"name": "Deepseek R1 Distill Qwen 1.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
"description": "Open source model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. 1446 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1446,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"arxiv:2501.12948",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-distill-qwen-1.5b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-v3",
"name": "Deepseek V3",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-V3",
"description": "Open source model deepseek-ai/DeepSeek-V3. 4024 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4024,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v3",
"conversational",
"custom_code",
"arxiv:2412.19437",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-v3"
},
{
"slug": "gpt2-large",
"name": "Gpt2 Large",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/openai-community/gpt2-large",
"description": "Open source model openai-community/gpt2-large. 344 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 344,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"onnx",
"safetensors",
"gpt2",
"en",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt2-large"
},
{
"slug": "glm-4.7-flash-mlx-8bit",
"name": "Glm 4.7 Flash Mlx 8Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/GLM-4.7-Flash-MLX-8bit",
"description": "Open source model lmstudio-community/GLM-4.7-Flash-MLX-8bit. 9 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 9,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm4_moe_lite",
"mlx",
"conversational",
"en",
"zh",
"base_model:zai-org/GLM-4.7-Flash",
"base_model:quantized:zai-org/GLM-4.7-Flash",
"endpoints_compatible",
"8-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.7-flash-mlx-8bit"
},
{
"slug": "glm-4.7-flash-mlx-6bit",
"name": "Glm 4.7 Flash Mlx 6Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/GLM-4.7-Flash-MLX-6bit",
"description": "Open source model lmstudio-community/GLM-4.7-Flash-MLX-6bit. 7 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 7,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm4_moe_lite",
"mlx",
"conversational",
"en",
"zh",
"base_model:zai-org/GLM-4.7-Flash",
"base_model:quantized:zai-org/GLM-4.7-Flash",
"endpoints_compatible",
"6-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.7-flash-mlx-6bit"
},
{
"slug": "qwen3-0.6b-fp8",
"name": "Qwen3 0.6B Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-0.6B-FP8",
"description": "Open source model Qwen/Qwen3-0.6B-FP8. 56 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 56,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-0.6B",
"base_model:quantized:Qwen/Qwen3-0.6B",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-0.6b-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "llama-3.1-8b",
"name": "Llama 3.1 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.1-8B",
"description": "Open source model meta-llama/Llama-3.1-8B. 2065 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2065,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.1-8b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "pythia-160m",
"name": "Pythia 160M",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/EleutherAI/pythia-160m",
"description": "Open source model EleutherAI/pythia-160m. 38 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 38,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"causal-lm",
"pythia",
"en",
"dataset:EleutherAI/pile",
"arxiv:2304.01373",
"arxiv:2101.00027",
"arxiv:2201.07311",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "pythia-160m"
},
{
"slug": "deepseek-r1-distill-qwen-32b",
"name": "Deepseek R1 Distill Qwen 32B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
"description": "Open source model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. 1517 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1517,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"arxiv:2501.12948",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-distill-qwen-32b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "hunyuanocr",
"name": "Hunyuanocr",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/tencent/HunyuanOCR",
"description": "Open source model tencent/HunyuanOCR. 553 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 553,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"hunyuan_vl",
"ocr",
"hunyuan",
"vision-language",
"image-to-text",
"1B",
"end-to-end",
"image-text-to-text",
"conversational",
"multilingual",
"arxiv:2511.19575",
"base_model:tencent/HunyuanOCR",
"base_model:finetune:tencent/HunyuanOCR",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "hunyuanocr"
},
{
"slug": "qwen3-30b-a3b",
"name": "Qwen3 30B A3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-30B-A3B",
"description": "Open source model Qwen/Qwen3-30B-A3B. 855 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 855,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-30B-A3B-Base",
"base_model:finetune:Qwen/Qwen3-30B-A3B-Base",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-30b-a3b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-0.5b",
"name": "Qwen2.5 0.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-0.5B",
"description": "Open source model Qwen/Qwen2.5-0.5B. 372 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 372,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"en",
"arxiv:2407.10671",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-0.5b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-32b-instruct-awq",
"name": "Qwen2.5 32B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-32B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-32B-Instruct-AWQ. 94 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 94,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-32B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-32B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-32b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "nvidia-nemotron-3-nano-30b-a3b-fp8",
"name": "Nvidia Nemotron 3 Nano 30B A3B Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
"description": "Open source model nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8. 284 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 284,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"nemotron_h",
"feature-extraction",
"nvidia",
"pytorch",
"conversational",
"custom_code",
"en",
"es",
"fr",
"de",
"ja",
"it",
"dataset:nvidia/Nemotron-Pretraining-Code-v1",
"dataset:nvidia/Nemotron-CC-v2",
"dataset:nvidia/Nemotron-Pretraining-SFT-v1",
"dataset:nvidia/Nemotron-CC-Math-v1",
"dataset:nvidia/Nemotron-Pretraining-Code-v2",
"dataset:nvidia/Nemotron-Pretraining-Specialized-v1",
"dataset:nvidia/Nemotron-CC-v2.1",
"dataset:nvidia/Nemotron-CC-Code-v1",
"dataset:nvidia/Nemotron-Pretraining-Dataset-sample",
"dataset:nvidia/Nemotron-Competitive-Programming-v1",
"dataset:nvidia/Nemotron-Math-v2",
"dataset:nvidia/Nemotron-Agentic-v1",
"dataset:nvidia/Nemotron-Math-Proofs-v1",
"dataset:nvidia/Nemotron-Instruction-Following-Chat-v1",
"dataset:nvidia/Nemotron-Science-v1",
"dataset:nvidia/Nemotron-3-Nano-RL-Training-Blend",
"arxiv:2512.20848",
"arxiv:2512.20856",
"base_model:nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
"base_model:quantized:nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
"eval-results",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "nvidia-nemotron-3-nano-30b-a3b-fp8"
},
{
"slug": "qwen2.5-14b-instruct",
"name": "Qwen2.5 14B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-14B-Instruct",
"description": "Open source model Qwen/Qwen2.5-14B-Instruct. 312 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 312,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-14B",
"base_model:finetune:Qwen/Qwen2.5-14B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-14b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "nvidia-nemotron-3-nano-30b-a3b-bf16",
"name": "Nvidia Nemotron 3 Nano 30B A3B Bf16",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
"description": "Open source model nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16. 634 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 634,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"nemotron_h",
"feature-extraction",
"nvidia",
"pytorch",
"conversational",
"custom_code",
"en",
"es",
"fr",
"de",
"ja",
"it",
"dataset:nvidia/Nemotron-Pretraining-Code-v1",
"dataset:nvidia/Nemotron-CC-v2",
"dataset:nvidia/Nemotron-Pretraining-SFT-v1",
"dataset:nvidia/Nemotron-CC-Math-v1",
"dataset:nvidia/Nemotron-Pretraining-Code-v2",
"dataset:nvidia/Nemotron-Pretraining-Specialized-v1",
"dataset:nvidia/Nemotron-CC-v2.1",
"dataset:nvidia/Nemotron-CC-Code-v1",
"dataset:nvidia/Nemotron-Pretraining-Dataset-sample",
"dataset:nvidia/Nemotron-Competitive-Programming-v1",
"dataset:nvidia/Nemotron-Math-v2",
"dataset:nvidia/Nemotron-Agentic-v1",
"dataset:nvidia/Nemotron-Math-Proofs-v1",
"dataset:nvidia/Nemotron-Instruction-Following-Chat-v1",
"dataset:nvidia/Nemotron-Science-v1",
"dataset:nvidia/Nemotron-3-Nano-RL-Training-Blend",
"arxiv:2512.20848",
"arxiv:2512.20856",
"eval-results",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "nvidia-nemotron-3-nano-30b-a3b-bf16"
},
{
"slug": "openelm-1_1b-instruct",
"name": "Openelm 1_1B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/apple/OpenELM-1_1B-Instruct",
"description": "Open source model apple/OpenELM-1_1B-Instruct. 72 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 72,
"language": "Python",
"license": "apple-amlr",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"openelm",
"custom_code",
"arxiv:2404.14619",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "openelm-1_1b-instruct"
},
{
"slug": "tiny-random-llamaforcausallm",
"name": "Tiny Random Llamaforcausallm",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/hmellor/tiny-random-LlamaForCausalLM",
"description": "Open source model hmellor/tiny-random-LlamaForCausalLM. 0 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 0,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tiny-random-llamaforcausallm",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-next-80b-a3b-instruct",
"name": "Qwen3 Next 80B A3B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct",
"description": "Open source model Qwen/Qwen3-Next-80B-A3B-Instruct. 937 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 937,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_next",
"conversational",
"arxiv:2309.00071",
"arxiv:2404.06654",
"arxiv:2505.09388",
"arxiv:2501.15383",
"eval-results",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 56,
"context_window_tokens": 4096,
"parameters_total_b": 80,
"parameters_active_b": 80,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-next-80b-a3b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "h2ovl-mississippi-800m",
"name": "H2Ovl Mississippi 800M",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/h2oai/h2ovl-mississippi-800m",
"description": "Open source model h2oai/h2ovl-mississippi-800m. 39 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 39,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"h2ovl_chat",
"feature-extraction",
"gpt",
"llm",
"multimodal large language model",
"ocr",
"conversational",
"custom_code",
"en",
"arxiv:2410.13611",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "h2ovl-mississippi-800m"
},
{
"slug": "bloomz-560m",
"name": "Bloomz 560M",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/bigscience/bloomz-560m",
"description": "Open source model bigscience/bloomz-560m. 137 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 137,
"language": "Python",
"license": "bigscience-bloom-rail-1.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"bloom",
"ak",
"ar",
"as",
"bm",
"bn",
"ca",
"code",
"en",
"es",
"eu",
"fon",
"fr",
"gu",
"hi",
"id",
"ig",
"ki",
"kn",
"lg",
"ln",
"ml",
"mr",
"ne",
"nso",
"ny",
"or",
"pa",
"pt",
"rn",
"rw",
"sn",
"st",
"sw",
"ta",
"te",
"tn",
"ts",
"tum",
"tw",
"ur",
"vi",
"wo",
"xh",
"yo",
"zh",
"zu",
"dataset:bigscience/xP3",
"arxiv:2211.01786",
"model-index",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "bloomz-560m"
},
{
"slug": "qwen2.5-1.5b-quantized.w8a8",
"name": "Qwen2.5 1.5B Quantized.W8A8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/RedHatAI/Qwen2.5-1.5B-quantized.w8a8",
"description": "Open source model RedHatAI/Qwen2.5-1.5B-quantized.w8a8. 2 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"safetensors",
"qwen2",
"chat",
"neuralmagic",
"llmcompressor",
"conversational",
"en",
"base_model:Qwen/Qwen2.5-1.5B",
"base_model:quantized:Qwen/Qwen2.5-1.5B",
"8-bit",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-1.5b-quantized.w8a8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "h2ovl-mississippi-2b",
"name": "H2Ovl Mississippi 2B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/h2oai/h2ovl-mississippi-2b",
"description": "Open source model h2oai/h2ovl-mississippi-2b. 40 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 40,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"h2ovl_chat",
"feature-extraction",
"gpt",
"llm",
"multimodal large language model",
"ocr",
"conversational",
"custom_code",
"en",
"arxiv:2410.13611",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "h2ovl-mississippi-2b"
},
{
"slug": "llava-v1.5-7b",
"name": "Llava V1.5 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/liuhaotian/llava-v1.5-7b",
"description": "Open source model liuhaotian/llava-v1.5-7b. 537 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 537,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"llava",
"image-text-to-text",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llava-v1.5-7b"
},
{
"slug": "t5-3b",
"name": "T5 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/google-t5/t5-3b",
"description": "Open source model google-t5/t5-3b. 51 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 51,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"safetensors",
"t5",
"summarization",
"translation",
"en",
"fr",
"ro",
"de",
"multilingual",
"dataset:c4",
"arxiv:1805.12471",
"arxiv:1708.00055",
"arxiv:1704.05426",
"arxiv:1606.05250",
"arxiv:1808.09121",
"arxiv:1810.12885",
"arxiv:1905.10044",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "t5-3b"
},
{
"slug": "qwen2.5-14b-instruct-awq",
"name": "Qwen2.5 14B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-14B-Instruct-AWQ. 27 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 27,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-14B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-14B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-14b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "llama-3.2-3b",
"name": "Llama 3.2 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.2-3B",
"description": "Open source model meta-llama/Llama-3.2-3B. 697 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 697,
"language": "Python",
"license": "llama3.2",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-3b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "phi-3-mini-4k-instruct-gptq-4bit",
"name": "Phi 3 Mini 4K Instruct Gptq 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/kaitchup/Phi-3-mini-4k-instruct-gptq-4bit",
"description": "Open source model kaitchup/Phi-3-mini-4k-instruct-gptq-4bit. 2 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi3",
"conversational",
"custom_code",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-3-mini-4k-instruct-gptq-4bit",
"logo_url": "/logos/phi.svg"
},
{
"slug": "qwen2.5-72b-instruct-awq",
"name": "Qwen2.5 72B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-72B-Instruct-AWQ. 74 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 74,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-72B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-72B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 50,
"context_window_tokens": 4096,
"parameters_total_b": 72,
"parameters_active_b": 72,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-72b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "smollm2-135m",
"name": "Smollm2 135M",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/HuggingFaceTB/SmolLM2-135M",
"description": "Open source model HuggingFaceTB/SmolLM2-135M. 166 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 166,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"en",
"arxiv:2502.02737",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "smollm2-135m"
},
{
"slug": "llama-3.3-70b-instruct",
"name": "Llama 3.3 70B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct",
"description": "Open source model meta-llama/Llama-3.3-70B-Instruct. 2658 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2658,
"language": "Python",
"license": "llama3.3",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"de",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-3.1-70B",
"base_model:finetune:meta-llama/Llama-3.1-70B",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.3-70b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-30b-a3b-instruct-2507-fp8",
"name": "Qwen3 30B A3B Instruct 2507 Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507-FP8",
"description": "Open source model Qwen/Qwen3-30B-A3B-Instruct-2507-FP8. 112 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 112,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-30B-A3B-Instruct-2507",
"base_model:quantized:Qwen/Qwen3-30B-A3B-Instruct-2507",
"endpoints_compatible",
"fp8",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-30b-a3b-instruct-2507-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-coder-32b-instruct",
"name": "Qwen2.5 Coder 32B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct",
"description": "Open source model Qwen/Qwen2.5-Coder-32B-Instruct. 1995 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1995,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-32B",
"base_model:finetune:Qwen/Qwen2.5-Coder-32B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-32b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-235b-a22b-instruct-2507-fp8",
"name": "Qwen3 235B A22B Instruct 2507 Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
"description": "Open source model Qwen/Qwen3-235B-A22B-Instruct-2507-FP8. 145 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 145,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-235B-A22B-Instruct-2507",
"base_model:quantized:Qwen/Qwen3-235B-A22B-Instruct-2507",
"endpoints_compatible",
"fp8",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 164,
"context_window_tokens": 4096,
"parameters_total_b": 235,
"parameters_active_b": 235,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-235b-a22b-instruct-2507-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-r1-distill-qwen-7b",
"name": "Deepseek R1 Distill Qwen 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
"description": "Open source model deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. 787 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 787,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"arxiv:2501.12948",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-distill-qwen-7b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "phi-3-mini-4k-instruct",
"name": "Phi 3 Mini 4K Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct",
"description": "Open source model microsoft/Phi-3-mini-4k-instruct. 1386 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1386,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi3",
"nlp",
"code",
"conversational",
"custom_code",
"en",
"fr",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-3-mini-4k-instruct",
"logo_url": "/logos/phi.svg"
},
{
"slug": "qwen3-14b",
"name": "Qwen3 14B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-14B",
"description": "Open source model Qwen/Qwen3-14B. 366 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 366,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-14B-Base",
"base_model:finetune:Qwen/Qwen3-14B-Base",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-14b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-coder-1.5b",
"name": "Qwen2.5 Coder 1.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B",
"description": "Open source model Qwen/Qwen2.5-Coder-1.5B. 81 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 81,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"qwen",
"qwen-coder",
"codeqwen",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-1.5B",
"base_model:finetune:Qwen/Qwen2.5-1.5B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-1.5b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "llama-3.1-70b-instruct",
"name": "Llama 3.1 70B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct",
"description": "Open source model meta-llama/Llama-3.1-70B-Instruct. 890 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 890,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-3.1-70B",
"base_model:finetune:meta-llama/Llama-3.1-70B",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.1-70b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "hunyuanimage-3.0",
"name": "Hunyuanimage 3.0",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/tencent/HunyuanImage-3.0",
"description": "Open source model tencent/HunyuanImage-3.0. 640 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 640,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"hunyuan_image_3_moe",
"text-to-image",
"custom_code",
"arxiv:2509.23951",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "hunyuanimage-3.0"
},
{
"slug": "qwen2.5-coder-7b-instruct-awq",
"name": "Qwen2.5 Coder 7B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-Coder-7B-Instruct-AWQ. 19 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 19,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-7B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-7B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-7b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-coder-30b-a3b-instruct",
"name": "Qwen3 Coder 30B A3B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct",
"description": "Open source model Qwen/Qwen3-Coder-30B-A3B-Instruct. 945 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 945,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2505.09388",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-coder-30b-a3b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-r1-0528",
"name": "Deepseek R1 0528",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528",
"description": "Open source model deepseek-ai/DeepSeek-R1-0528. 2400 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2400,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v3",
"conversational",
"custom_code",
"arxiv:2501.12948",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-0528"
},
{
"slug": "tiny-random-llama-3",
"name": "Tiny Random Llama 3",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/llamafactory/tiny-random-Llama-3",
"description": "Open source model llamafactory/tiny-random-Llama-3. 3 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"text-generation-inference",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tiny-random-llama-3",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen2.5-coder-32b-instruct-awq",
"name": "Qwen2.5 Coder 32B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-Coder-32B-Instruct-AWQ. 33 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 33,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-32B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-32B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-32b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "mistral-7b-instruct-v0.1",
"name": "Mistral 7B Instruct V0.1",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1",
"description": "Open source model mistralai/Mistral-7B-Instruct-v0.1. 1826 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1826,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"mistral",
"finetuned",
"mistral-common",
"conversational",
"arxiv:2310.06825",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:finetune:mistralai/Mistral-7B-v0.1",
"text-generation-inference",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "mistral-7b-instruct-v0.1",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "gpt-oss-20b-mxfp4-q8",
"name": "Gpt Oss 20B Mxfp4 Q8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/mlx-community/gpt-oss-20b-MXFP4-Q8",
"description": "Open source model mlx-community/gpt-oss-20b-MXFP4-Q8. 31 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 31,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"mlx",
"safetensors",
"gpt_oss",
"vllm",
"conversational",
"base_model:openai/gpt-oss-20b",
"base_model:quantized:openai/gpt-oss-20b",
"4-bit",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 14,
"context_window_tokens": 4096,
"parameters_total_b": 20,
"parameters_active_b": 20,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt-oss-20b-mxfp4-q8"
},
{
"slug": "qwen3-embedding-4b",
"name": "Qwen3 Embedding 4B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Embedding-4B",
"description": "Open source model Qwen/Qwen3-Embedding-4B. 224 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 224,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"sentence-transformers",
"safetensors",
"qwen3",
"transformers",
"sentence-similarity",
"feature-extraction",
"text-embeddings-inference",
"arxiv:2506.05176",
"base_model:Qwen/Qwen3-4B-Base",
"base_model:finetune:Qwen/Qwen3-4B-Base",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-embedding-4b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-1.5b-instruct-awq",
"name": "Qwen2.5 1.5B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-1.5B-Instruct-AWQ. 6 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 6,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-1.5B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-1.5B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-1.5b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "meta-llama-3.1-8b-instruct-fp8",
"name": "Meta Llama 3.1 8B Instruct Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8",
"description": "Open source model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8. 44 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 44,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"fp8",
"vllm",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:quantized:meta-llama/Llama-3.1-8B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3.1-8b-instruct-fp8",
"logo_url": "/logos/meta.svg"
},
{
"slug": "phi-4",
"name": "Phi 4",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/phi-4",
"description": "Open source model microsoft/phi-4. 2220 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2220,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi3",
"phi",
"nlp",
"math",
"code",
"chat",
"conversational",
"en",
"arxiv:2412.08905",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-4",
"logo_url": "/logos/phi.svg"
},
{
"slug": "deepseek-r1",
"name": "Deepseek R1",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1",
"description": "Open source model deepseek-ai/DeepSeek-R1. 13011 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 13011,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v3",
"conversational",
"custom_code",
"arxiv:2501.12948",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1"
},
{
"slug": "llama-3.2-1b-instruct-fp8",
"name": "Llama 3.2 1B Instruct Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/RedHatAI/Llama-3.2-1B-Instruct-FP8",
"description": "Open source model RedHatAI/Llama-3.2-1B-Instruct-FP8. 3 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3,
"language": "Python",
"license": "llama3.2",
"tags": [
"AI",
"LLM",
"safetensors",
"llama",
"llama-3",
"neuralmagic",
"llmcompressor",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:quantized:meta-llama/Llama-3.2-1B-Instruct",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-1b-instruct-fp8",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-3.1-405b",
"name": "Llama 3.1 405B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-3.1-405B",
"description": "Open source model meta-llama/Llama-3.1-405B. 961 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 961,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"pytorch",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 284,
"context_window_tokens": 4096,
"parameters_total_b": 405,
"parameters_active_b": 405,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.1-405b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-4b-thinking-2507",
"name": "Qwen3 4B Thinking 2507",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507",
"description": "Open source model Qwen/Qwen3-4B-Thinking-2507. 548 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 548,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-4b-thinking-2507",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "gpt2-medium",
"name": "Gpt2 Medium",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/openai-community/gpt2-medium",
"description": "Open source model openai-community/gpt2-medium. 193 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 193,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"onnx",
"safetensors",
"gpt2",
"en",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt2-medium"
},
{
"slug": "tiny-gpt2",
"name": "Tiny Gpt2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/sshleifer/tiny-gpt2",
"description": "Open source model sshleifer/tiny-gpt2. 34 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 34,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"gpt2",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tiny-gpt2"
},
{
"slug": "hermes-3-llama-3.1-8b",
"name": "Hermes 3 Llama 3.1 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B",
"description": "Open source model NousResearch/Hermes-3-Llama-3.1-8B. 385 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 385,
"language": "Python",
"license": "llama3",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"Llama-3",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"roleplaying",
"chat",
"conversational",
"en",
"arxiv:2408.11857",
"base_model:meta-llama/Llama-3.1-8B",
"base_model:finetune:meta-llama/Llama-3.1-8B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "hermes-3-llama-3.1-8b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "phi-3.5-vision-instruct",
"name": "Phi 3.5 Vision Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/Phi-3.5-vision-instruct",
"description": "Open source model microsoft/Phi-3.5-vision-instruct. 726 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 726,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi3_v",
"nlp",
"code",
"vision",
"image-text-to-text",
"conversational",
"custom_code",
"multilingual",
"arxiv:2404.14219",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": true
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-3.5-vision-instruct",
"logo_url": "/logos/phi.svg"
},
{
"slug": "minimax-m2",
"name": "Minimax M2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/MiniMaxAI/MiniMax-M2",
"description": "Open source model MiniMaxAI/MiniMax-M2. 1485 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1485,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"minimax_m2",
"conversational",
"custom_code",
"arxiv:2504.07164",
"arxiv:2509.06501",
"arxiv:2509.13160",
"eval-results",
"endpoints_compatible",
"fp8",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "minimax-m2"
},
{
"slug": "deepseek-r1-distill-llama-8b",
"name": "Deepseek R1 Distill Llama 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
"description": "Open source model deepseek-ai/DeepSeek-R1-Distill-Llama-8B. 843 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 843,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"arxiv:2501.12948",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-distill-llama-8b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-14b-awq",
"name": "Qwen3 14B Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-14B-AWQ",
"description": "Open source model Qwen/Qwen3-14B-AWQ. 57 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 57,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-14B",
"base_model:quantized:Qwen/Qwen3-14B",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-14b-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-235b-a22b",
"name": "Qwen3 235B A22B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-235B-A22B",
"description": "Open source model Qwen/Qwen3-235B-A22B. 1075 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1075,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 164,
"context_window_tokens": 4096,
"parameters_total_b": 235,
"parameters_active_b": 235,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-235b-a22b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "meta-llama-3.1-8b-instruct-awq-int4",
"name": "Meta Llama 3.1 8B Instruct Awq Int4",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"description": "Open source model hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4. 87 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 87,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"llama-3.1",
"meta",
"autoawq",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3.1-8b-instruct-awq-int4",
"logo_url": "/logos/meta.svg"
},
{
"slug": "lfm2.5-1.2b-instruct-mlx-8bit",
"name": "Lfm2.5 1.2B Instruct Mlx 8Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/LFM2.5-1.2B-Instruct-MLX-8bit",
"description": "Open source model lmstudio-community/LFM2.5-1.2B-Instruct-MLX-8bit. 1 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"lfm2",
"liquid",
"lfm2.5",
"edge",
"mlx",
"conversational",
"en",
"ar",
"zh",
"fr",
"de",
"ja",
"ko",
"es",
"base_model:LiquidAI/LFM2.5-1.2B-Instruct",
"base_model:quantized:LiquidAI/LFM2.5-1.2B-Instruct",
"endpoints_compatible",
"8-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "lfm2.5-1.2b-instruct-mlx-8bit"
},
{
"slug": "glm-4.7-flash-gguf",
"name": "Glm 4.7 Flash Gguf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/GLM-4.7-Flash-GGUF",
"description": "Open source model unsloth/GLM-4.7-Flash-GGUF. 482 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 482,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"gguf",
"unsloth",
"en",
"zh",
"arxiv:2508.06471",
"base_model:zai-org/GLM-4.7-Flash",
"base_model:quantized:zai-org/GLM-4.7-Flash",
"endpoints_compatible",
"deploy:azure",
"region:us",
"imatrix",
"conversational"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.7-flash-gguf"
},
{
"slug": "deepseek-r1-distill-qwen-14b",
"name": "Deepseek R1 Distill Qwen 14B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
"description": "Open source model deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. 603 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 603,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"arxiv:2501.12948",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-distill-qwen-14b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "lfm2.5-1.2b-instruct-mlx-6bit",
"name": "Lfm2.5 1.2B Instruct Mlx 6Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/LFM2.5-1.2B-Instruct-MLX-6bit",
"description": "Open source model lmstudio-community/LFM2.5-1.2B-Instruct-MLX-6bit. 4 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"lfm2",
"liquid",
"lfm2.5",
"edge",
"mlx",
"conversational",
"en",
"ar",
"zh",
"fr",
"de",
"ja",
"ko",
"es",
"base_model:LiquidAI/LFM2.5-1.2B-Instruct",
"base_model:quantized:LiquidAI/LFM2.5-1.2B-Instruct",
"endpoints_compatible",
"6-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "lfm2.5-1.2b-instruct-mlx-6bit"
},
{
"slug": "lfm2.5-1.2b-instruct-mlx-4bit",
"name": "Lfm2.5 1.2B Instruct Mlx 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/LFM2.5-1.2B-Instruct-MLX-4bit",
"description": "Open source model lmstudio-community/LFM2.5-1.2B-Instruct-MLX-4bit. 1 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"lfm2",
"liquid",
"lfm2.5",
"edge",
"mlx",
"conversational",
"en",
"ar",
"zh",
"fr",
"de",
"ja",
"ko",
"es",
"base_model:LiquidAI/LFM2.5-1.2B-Instruct",
"base_model:quantized:LiquidAI/LFM2.5-1.2B-Instruct",
"endpoints_compatible",
"4-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "lfm2.5-1.2b-instruct-mlx-4bit"
},
{
"slug": "vicuna-7b-v1.5",
"name": "Vicuna 7B V1.5",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmsys/vicuna-7b-v1.5",
"description": "Open source model lmsys/vicuna-7b-v1.5. 387 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 387,
"language": "Python",
"license": "llama2",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"llama",
"arxiv:2307.09288",
"arxiv:2306.05685",
"text-generation-inference",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "vicuna-7b-v1.5"
},
{
"slug": "llama-3.2-1b-instruct-q8_0-gguf",
"name": "Llama 3.2 1B Instruct Q8_0 Gguf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF",
"description": "Open source model hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF. 43 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 43,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"llama-cpp",
"gguf-my-repo",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:quantized:meta-llama/Llama-3.2-1B-Instruct",
"endpoints_compatible",
"region:us",
"conversational"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.2-1b-instruct-q8_0-gguf",
"logo_url": "/logos/meta.svg"
},
{
"slug": "llama-3.3-70b-instruct-awq",
"name": "Llama 3.3 70B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/kosbu/Llama-3.3-70B-Instruct-AWQ",
"description": "Open source model kosbu/Llama-3.3-70B-Instruct-AWQ. 10 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 10,
"language": "Python",
"license": "llama3.3",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"facebook",
"meta",
"llama-3",
"awq",
"conversational",
"en",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"de",
"base_model:meta-llama/Llama-3.3-70B-Instruct",
"base_model:quantized:meta-llama/Llama-3.3-70B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-3.3-70b-instruct-awq",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-32b-fp8",
"name": "Qwen3 32B Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-32B-FP8",
"description": "Open source model Qwen/Qwen3-32B-FP8. 80 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 80,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-32B",
"base_model:quantized:Qwen/Qwen3-32B",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-32b-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "gpt2-xl",
"name": "Gpt2 Xl",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/openai-community/gpt2-xl",
"description": "Open source model openai-community/gpt2-xl. 373 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 373,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"safetensors",
"gpt2",
"en",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt2-xl"
},
{
"slug": "qwen3-4b-instruct-2507-fp8",
"name": "Qwen3 4B Instruct 2507 Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507-FP8",
"description": "Open source model Qwen/Qwen3-4B-Instruct-2507-FP8. 65 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 65,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:quantized:Qwen/Qwen3-4B-Instruct-2507",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-4b-instruct-2507-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "xlnet-base-cased",
"name": "Xlnet Base Cased",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/xlnet/xlnet-base-cased",
"description": "Open source model xlnet/xlnet-base-cased. 80 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 80,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"rust",
"xlnet",
"en",
"dataset:bookcorpus",
"dataset:wikipedia",
"arxiv:1906.08237",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "xlnet-base-cased"
},
{
"slug": "llama-2-7b-hf",
"name": "Llama 2 7B Hf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-2-7b-hf",
"description": "Open source model meta-llama/Llama-2-7b-hf. 2268 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2268,
"language": "Python",
"license": "llama2",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"llama",
"facebook",
"meta",
"llama-2",
"en",
"arxiv:2307.09288",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-2-7b-hf",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen2.5-math-7b-instruct",
"name": "Qwen2.5 Math 7B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct",
"description": "Open source model Qwen/Qwen2.5-Math-7B-Instruct. 89 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 89,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2409.12122",
"base_model:Qwen/Qwen2.5-Math-7B",
"base_model:finetune:Qwen/Qwen2.5-Math-7B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-math-7b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-reranker-0.6b",
"name": "Qwen3 Reranker 0.6B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Reranker-0.6B",
"description": "Open source model Qwen/Qwen3-Reranker-0.6B. 305 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 305,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"text-ranking",
"arxiv:2506.05176",
"base_model:Qwen/Qwen3-0.6B-Base",
"base_model:finetune:Qwen/Qwen3-0.6B-Base",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-reranker-0.6b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-1.5b",
"name": "Qwen2.5 1.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-1.5B",
"description": "Open source model Qwen/Qwen2.5-1.5B. 165 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 165,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"en",
"arxiv:2407.10671",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-1.5b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-30b-a3b-thinking-2507",
"name": "Qwen3 30B A3B Thinking 2507",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507",
"description": "Open source model Qwen/Qwen3-30B-A3B-Thinking-2507. 359 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 359,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2402.17463",
"arxiv:2407.02490",
"arxiv:2501.15383",
"arxiv:2404.06654",
"arxiv:2505.09388",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-30b-a3b-thinking-2507",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "smollm2-135m-instruct",
"name": "Smollm2 135M Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct",
"description": "Open source model HuggingFaceTB/SmolLM2-135M-Instruct. 292 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 292,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"tensorboard",
"onnx",
"safetensors",
"llama",
"transformers.js",
"conversational",
"en",
"arxiv:2502.02737",
"base_model:HuggingFaceTB/SmolLM2-135M",
"base_model:quantized:HuggingFaceTB/SmolLM2-135M",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "smollm2-135m-instruct"
},
{
"slug": "qwen2.5-math-1.5b",
"name": "Qwen2.5 Math 1.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Math-1.5B",
"description": "Open source model Qwen/Qwen2.5-Math-1.5B. 100 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 100,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"conversational",
"en",
"arxiv:2409.12122",
"base_model:Qwen/Qwen2.5-1.5B",
"base_model:finetune:Qwen/Qwen2.5-1.5B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-math-1.5b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "glm-4.5-air-awq-4bit",
"name": "Glm 4.5 Air Awq 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/cyankiwi/GLM-4.5-Air-AWQ-4bit",
"description": "Open source model cyankiwi/GLM-4.5-Air-AWQ-4bit. 27 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 27,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm4_moe",
"conversational",
"en",
"zh",
"arxiv:2508.06471",
"base_model:zai-org/GLM-4.5-Air",
"base_model:quantized:zai-org/GLM-4.5-Air",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.5-air-awq-4bit"
},
{
"slug": "llama-2-7b-chat-hf",
"name": "Llama 2 7B Chat Hf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-2-7b-chat-hf",
"description": "Open source model meta-llama/Llama-2-7b-chat-hf. 4705 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4705,
"language": "Python",
"license": "llama2",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"llama",
"facebook",
"meta",
"llama-2",
"conversational",
"en",
"arxiv:2307.09288",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-2-7b-chat-hf",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen2.5-coder-7b-instruct-gptq-int4",
"name": "Qwen2.5 Coder 7B Instruct Gptq Int4",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4",
"description": "Open source model Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4. 12 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 12,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-7B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-Coder-7B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"gptq",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-7b-instruct-gptq-int4",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-vl-30b-a3b-instruct-awq",
"name": "Qwen3 Vl 30B A3B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ",
"description": "Open source model QuantTrio/Qwen3-VL-30B-A3B-Instruct-AWQ. 38 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 38,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_vl_moe",
"image-text-to-text",
"AWQ",
"vLLM",
"conversational",
"arxiv:2505.09388",
"arxiv:2502.13923",
"arxiv:2409.12191",
"arxiv:2308.12966",
"base_model:Qwen/Qwen3-VL-30B-A3B-Instruct",
"base_model:quantized:Qwen/Qwen3-VL-30B-A3B-Instruct",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-vl-30b-a3b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-8b-base",
"name": "Qwen3 8B Base",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-8B-Base",
"description": "Open source model Qwen/Qwen3-8B-Base. 82 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 82,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-8b-base",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-coder-14b-instruct",
"name": "Qwen2.5 Coder 14B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct",
"description": "Open source model Qwen/Qwen2.5-Coder-14B-Instruct. 140 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 140,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"codeqwen",
"chat",
"qwen",
"qwen-coder",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-Coder-14B",
"base_model:finetune:Qwen/Qwen2.5-Coder-14B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 10,
"context_window_tokens": 4096,
"parameters_total_b": 14,
"parameters_active_b": 14,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-14b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "stories15m_moe",
"name": "Stories15M_Moe",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/ggml-org/stories15M_MOE",
"description": "Open source model ggml-org/stories15M_MOE. 5 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 5,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gguf",
"mixtral",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "stories15m_moe"
},
{
"slug": "opt-1.3b",
"name": "Opt 1.3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/facebook/opt-1.3b",
"description": "Open source model facebook/opt-1.3b. 182 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 182,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"opt",
"en",
"arxiv:2205.01068",
"arxiv:2005.14165",
"text-generation-inference",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "opt-1.3b"
},
{
"slug": "minimax-m2-awq",
"name": "Minimax M2 Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/QuantTrio/MiniMax-M2-AWQ",
"description": "Open source model QuantTrio/MiniMax-M2-AWQ. 8 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 8,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"mixtral",
"vLLM",
"AWQ",
"conversational",
"arxiv:2504.07164",
"arxiv:2509.06501",
"arxiv:2509.13160",
"base_model:MiniMaxAI/MiniMax-M2",
"base_model:quantized:MiniMaxAI/MiniMax-M2",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "minimax-m2-awq"
},
{
"slug": "glm-4.7-flash-nvfp4",
"name": "Glm 4.7 Flash Nvfp4",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/GadflyII/GLM-4.7-Flash-NVFP4",
"description": "Open source model GadflyII/GLM-4.7-Flash-NVFP4. 62 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 62,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm4_moe_lite",
"moe",
"nvfp4",
"quantized",
"vllm",
"glm",
"30b",
"conversational",
"en",
"zh",
"base_model:zai-org/GLM-4.7-Flash",
"base_model:quantized:zai-org/GLM-4.7-Flash",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.7-flash-nvfp4"
},
{
"slug": "hy-mt1.5-7b",
"name": "Hy Mt1.5 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/tencent/HY-MT1.5-7B",
"description": "Open source model tencent/HY-MT1.5-7B. 133 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 133,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"hunyuan_v1_dense",
"translation",
"zh",
"en",
"fr",
"pt",
"es",
"ja",
"tr",
"ru",
"ar",
"ko",
"th",
"it",
"de",
"vi",
"ms",
"id",
"tl",
"hi",
"pl",
"cs",
"nl",
"km",
"my",
"fa",
"gu",
"ur",
"te",
"mr",
"he",
"bn",
"ta",
"uk",
"bo",
"kk",
"mn",
"ug",
"arxiv:2512.24092",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "hy-mt1.5-7b"
},
{
"slug": "gemma-2-27b-it",
"name": "Gemma 2 27B It",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/google/gemma-2-27b-it",
"description": "Open source model google/gemma-2-27b-it. 559 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 559,
"language": "Python",
"license": "gemma",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gemma2",
"conversational",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:2110.08193",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:1804.06876",
"arxiv:2103.03874",
"arxiv:2304.06364",
"arxiv:2206.04615",
"arxiv:2203.09509",
"base_model:google/gemma-2-27b",
"base_model:finetune:google/gemma-2-27b",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 19,
"context_window_tokens": 4096,
"parameters_total_b": 27,
"parameters_active_b": 27,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gemma-2-27b-it",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "qwen3-coder-next-gguf",
"name": "Qwen3 Coder Next Gguf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/Qwen3-Coder-Next-GGUF",
"description": "Open source model unsloth/Qwen3-Coder-Next-GGUF. 347 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 347,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"gguf",
"qwen3_next",
"unsloth",
"qwen",
"qwen3",
"base_model:Qwen/Qwen3-Coder-Next",
"base_model:quantized:Qwen/Qwen3-Coder-Next",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-coder-next-gguf",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "gte-qwen2-1.5b-instruct",
"name": "Gte Qwen2 1.5B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct",
"description": "Open source model Alibaba-NLP/gte-Qwen2-1.5B-instruct. 229 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 229,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"sentence-transformers",
"safetensors",
"qwen2",
"mteb",
"transformers",
"Qwen2",
"sentence-similarity",
"custom_code",
"arxiv:2308.03281",
"model-index",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gte-qwen2-1.5b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "lfm2-1.2b",
"name": "Lfm2 1.2B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/LiquidAI/LFM2-1.2B",
"description": "Open source model LiquidAI/LFM2-1.2B. 349 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 349,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"lfm2",
"liquid",
"edge",
"conversational",
"en",
"ar",
"zh",
"fr",
"de",
"ja",
"ko",
"es",
"arxiv:2511.23404",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "lfm2-1.2b"
},
{
"slug": "saiga_llama3_8b",
"name": "Saiga_Llama3_8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/IlyaGusev/saiga_llama3_8b",
"description": "Open source model IlyaGusev/saiga_llama3_8b. 137 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 137,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"ru",
"dataset:IlyaGusev/saiga_scored",
"doi:10.57967/hf/2368",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "saiga_llama3_8b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen3-1.7b-base",
"name": "Qwen3 1.7B Base",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-1.7B-Base",
"description": "Open source model Qwen/Qwen3-1.7B-Base. 62 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 62,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-1.7b-base",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "mistral-7b-v0.3-bnb-4bit",
"name": "Mistral 7B V0.3 Bnb 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit",
"description": "Open source model unsloth/mistral-7b-v0.3-bnb-4bit. 22 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 22,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"mistral",
"unsloth",
"mistral-7b",
"en",
"base_model:mistralai/Mistral-7B-v0.3",
"base_model:quantized:mistralai/Mistral-7B-v0.3",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "mistral-7b-v0.3-bnb-4bit",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "gemma-2-2b-it",
"name": "Gemma 2 2B It",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/google/gemma-2-2b-it",
"description": "Open source model google/gemma-2-2b-it. 1285 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1285,
"language": "Python",
"license": "gemma",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gemma2",
"conversational",
"arxiv:2009.03300",
"arxiv:1905.07830",
"arxiv:1911.11641",
"arxiv:1904.09728",
"arxiv:1905.10044",
"arxiv:1907.10641",
"arxiv:1811.00937",
"arxiv:1809.02789",
"arxiv:1911.01547",
"arxiv:1705.03551",
"arxiv:2107.03374",
"arxiv:2108.07732",
"arxiv:2110.14168",
"arxiv:2009.11462",
"arxiv:2101.11718",
"arxiv:2110.08193",
"arxiv:1804.09301",
"arxiv:2109.07958",
"arxiv:1804.06876",
"arxiv:2103.03874",
"arxiv:2304.06364",
"arxiv:1903.00161",
"arxiv:2206.04615",
"arxiv:2203.09509",
"arxiv:2403.13793",
"base_model:google/gemma-2-2b",
"base_model:finetune:google/gemma-2-2b",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 2,
"parameters_active_b": 2,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gemma-2-2b-it",
"logo_url": "/logos/gemma.svg"
},
{
"slug": "phi-4-multimodal-instruct",
"name": "Phi 4 Multimodal Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/Phi-4-multimodal-instruct",
"description": "Open source model microsoft/Phi-4-multimodal-instruct. 1573 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1573,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi4mm",
"nlp",
"code",
"audio",
"automatic-speech-recognition",
"speech-summarization",
"speech-translation",
"visual-question-answering",
"phi-4-multimodal",
"phi",
"phi-4-mini",
"custom_code",
"multilingual",
"ar",
"zh",
"cs",
"da",
"nl",
"en",
"fi",
"fr",
"de",
"he",
"hu",
"it",
"ja",
"ko",
"no",
"pl",
"pt",
"ru",
"es",
"sv",
"th",
"tr",
"uk",
"arxiv:2503.01743",
"arxiv:2407.13833",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-4-multimodal-instruct",
"logo_url": "/logos/phi.svg"
},
{
"slug": "pythia-70m-deduped",
"name": "Pythia 70M Deduped",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/EleutherAI/pythia-70m-deduped",
"description": "Open source model EleutherAI/pythia-70m-deduped. 27 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 27,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"causal-lm",
"pythia",
"en",
"dataset:EleutherAI/the_pile_deduplicated",
"arxiv:2304.01373",
"arxiv:2101.00027",
"arxiv:2201.07311",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "pythia-70m-deduped"
},
{
"slug": "dialogpt-medium",
"name": "Dialogpt Medium",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/DialoGPT-medium",
"description": "Open source model microsoft/DialoGPT-medium. 433 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 433,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"gpt2",
"conversational",
"arxiv:1911.00536",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "dialogpt-medium"
},
{
"slug": "gpt-oss-20b-bf16",
"name": "Gpt Oss 20B Bf16",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/gpt-oss-20b-BF16",
"description": "Open source model unsloth/gpt-oss-20b-BF16. 29 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 29,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"gpt_oss",
"vllm",
"unsloth",
"conversational",
"base_model:openai/gpt-oss-20b",
"base_model:finetune:openai/gpt-oss-20b",
"endpoints_compatible",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 14,
"context_window_tokens": 4096,
"parameters_total_b": 20,
"parameters_active_b": 20,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "gpt-oss-20b-bf16"
},
{
"slug": "qwen2.5-72b-instruct",
"name": "Qwen2.5 72B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct",
"description": "Open source model Qwen/Qwen2.5-72B-Instruct. 910 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 910,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-72B",
"base_model:finetune:Qwen/Qwen2.5-72B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 50,
"context_window_tokens": 4096,
"parameters_total_b": 72,
"parameters_active_b": 72,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-72b-instruct",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-32b-awq",
"name": "Qwen3 32B Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-32B-AWQ",
"description": "Open source model Qwen/Qwen3-32B-AWQ. 125 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 125,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-32B",
"base_model:quantized:Qwen/Qwen3-32B",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-32b-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "mimo-v2-flash",
"name": "Mimo V2 Flash",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash",
"description": "Open source model XiaomiMiMo/MiMo-V2-Flash. 628 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 628,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"mimo_v2_flash",
"conversational",
"custom_code",
"eval-results",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "mimo-v2-flash"
},
{
"slug": "qwen3-coder-30b-a3b-instruct-fp8",
"name": "Qwen3 Coder 30B A3B Instruct Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8",
"description": "Open source model Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8. 158 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 158,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2505.09388",
"endpoints_compatible",
"fp8",
"deploy:azure",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-coder-30b-a3b-instruct-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen3-8b-fp8",
"name": "Qwen3 8B Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-8B-FP8",
"description": "Open source model Qwen/Qwen3-8B-FP8. 56 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 56,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-8B",
"base_model:quantized:Qwen/Qwen3-8B",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-8b-fp8",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-v3.2",
"name": "Deepseek V3.2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2",
"description": "Open source model deepseek-ai/DeepSeek-V3.2. 1251 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1251,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v32",
"conversational",
"base_model:deepseek-ai/DeepSeek-V3.2-Exp-Base",
"base_model:finetune:deepseek-ai/DeepSeek-V3.2-Exp-Base",
"eval-results",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-v3.2"
},
{
"slug": "qwen3-coder-next",
"name": "Qwen3 Coder Next",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Coder-Next",
"description": "Open source model Qwen/Qwen3-Coder-Next. 912 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 912,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_next",
"conversational",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-coder-next",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2-0.5b",
"name": "Qwen2 0.5B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2-0.5B",
"description": "Open source model Qwen/Qwen2-0.5B. 164 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 164,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"pretrained",
"conversational",
"en",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 5,
"parameters_active_b": 5,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2-0.5b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "mistral-7b-v0.1",
"name": "Mistral 7B V0.1",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/mistralai/Mistral-7B-v0.1",
"description": "Open source model mistralai/Mistral-7B-v0.1. 4042 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 4042,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"mistral",
"pretrained",
"mistral-common",
"en",
"arxiv:2310.06825",
"text-generation-inference",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "mistral-7b-v0.1",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "kimi-k2-thinking",
"name": "Kimi K2 Thinking",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/moonshotai/Kimi-K2-Thinking",
"description": "Open source model moonshotai/Kimi-K2-Thinking. 1670 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1670,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"kimi_k2",
"conversational",
"custom_code",
"eval-results",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "kimi-k2-thinking"
},
{
"slug": "deepseek-r1-0528-qwen3-8b-mlx-4bit",
"name": "Deepseek R1 0528 Qwen3 8B Mlx 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit",
"description": "Open source model lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-4bit. 7 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 7,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"mlx",
"safetensors",
"qwen3",
"conversational",
"base_model:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"base_model:quantized:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"4-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-0528-qwen3-8b-mlx-4bit",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-7b-instruct-awq",
"name": "Qwen2.5 7B Instruct Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-AWQ",
"description": "Open source model Qwen/Qwen2.5-7B-Instruct-AWQ. 36 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 36,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-7B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-7b-instruct-awq",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "points-reader",
"name": "Points Reader",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/tencent/POINTS-Reader",
"description": "Open source model tencent/POINTS-Reader. 100 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 100,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"image-text-to-text",
"conversational",
"custom_code",
"arxiv:2509.01215",
"arxiv:2412.08443",
"arxiv:2409.04828",
"arxiv:2405.11850",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "points-reader"
},
{
"slug": "qwen3-4b-base",
"name": "Qwen3 4B Base",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-4B-Base",
"description": "Open source model Qwen/Qwen3-4B-Base. 80 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 80,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-4b-base",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "step-3.5-flash",
"name": "Step 3.5 Flash",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/stepfun-ai/Step-3.5-Flash",
"description": "Open source model stepfun-ai/Step-3.5-Flash. 621 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 621,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"step3p5",
"conversational",
"custom_code",
"arxiv:2602.10604",
"arxiv:2601.05593",
"arxiv:2507.19427",
"eval-results",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "step-3.5-flash"
},
{
"slug": "kogpt2-base-v2",
"name": "Kogpt2 Base V2",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/skt/kogpt2-base-v2",
"description": "Open source model skt/kogpt2-base-v2. 60 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 60,
"language": "Python",
"license": "cc-by-nc-sa-4.0",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"jax",
"gpt2",
"ko",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "kogpt2-base-v2"
},
{
"slug": "parler-tts-mini-multilingual-v1.1",
"name": "Parler Tts Mini Multilingual V1.1",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/parler-tts/parler-tts-mini-multilingual-v1.1",
"description": "Open source model parler-tts/parler-tts-mini-multilingual-v1.1. 54 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 54,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"parler_tts",
"text-to-speech",
"annotation",
"en",
"fr",
"es",
"pt",
"pl",
"de",
"nl",
"it",
"dataset:facebook/multilingual_librispeech",
"dataset:parler-tts/libritts_r_filtered",
"dataset:parler-tts/libritts-r-filtered-speaker-descriptions",
"dataset:parler-tts/mls_eng",
"dataset:parler-tts/mls-eng-speaker-descriptions",
"dataset:ylacombe/mls-annotated",
"dataset:ylacombe/cml-tts-filtered-annotated",
"dataset:PHBJT/cml-tts-filtered",
"arxiv:2402.01912",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "parler-tts-mini-multilingual-v1.1"
},
{
"slug": "qwen3-reranker-8b",
"name": "Qwen3 Reranker 8B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-Reranker-8B",
"description": "Open source model Qwen/Qwen3-Reranker-8B. 213 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 213,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"text-ranking",
"arxiv:2506.05176",
"base_model:Qwen/Qwen3-8B-Base",
"base_model:finetune:Qwen/Qwen3-8B-Base",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-reranker-8b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-r1-0528-qwen3-8b-mlx-8bit",
"name": "Deepseek R1 0528 Qwen3 8B Mlx 8Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bit",
"description": "Open source model lmstudio-community/DeepSeek-R1-0528-Qwen3-8B-MLX-8bit. 13 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 13,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"mlx",
"safetensors",
"qwen3",
"conversational",
"base_model:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"base_model:quantized:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
"8-bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-0528-qwen3-8b-mlx-8bit",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "powermoe-3b",
"name": "Powermoe 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/ibm-research/PowerMoE-3b",
"description": "Open source model ibm-research/PowerMoE-3b. 14 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 14,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"granitemoe",
"arxiv:2408.13359",
"model-index",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "powermoe-3b"
},
{
"slug": "llada-8b-instruct",
"name": "Llada 8B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/GSAI-ML/LLaDA-8B-Instruct",
"description": "Open source model GSAI-ML/LLaDA-8B-Instruct. 342 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 342,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llada",
"conversational",
"custom_code",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llada-8b-instruct"
},
{
"slug": "apertus-8b-instruct-2509",
"name": "Apertus 8B Instruct 2509",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509",
"description": "Open source model swiss-ai/Apertus-8B-Instruct-2509. 435 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 435,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"apertus",
"multilingual",
"compliant",
"swiss-ai",
"conversational",
"arxiv:2509.14233",
"base_model:swiss-ai/Apertus-8B-2509",
"base_model:finetune:swiss-ai/Apertus-8B-2509",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "apertus-8b-instruct-2509"
},
{
"slug": "qwen3-30b-a3b-gptq-int4",
"name": "Qwen3 30B A3B Gptq Int4",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-30B-A3B-GPTQ-Int4",
"description": "Open source model Qwen/Qwen3-30B-A3B-GPTQ-Int4. 45 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 45,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3_moe",
"conversational",
"arxiv:2309.00071",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-30B-A3B",
"base_model:quantized:Qwen/Qwen3-30B-A3B",
"endpoints_compatible",
"4-bit",
"gptq",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-30b-a3b-gptq-int4",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "tinyllama-1.1b-chat-v0.3-gptq",
"name": "Tinyllama 1.1B Chat V0.3 Gptq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ",
"description": "Open source model TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ. 9 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 9,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:OpenAssistant/oasst_top1_2023-08-25",
"base_model:TinyLlama/TinyLlama-1.1B-Chat-v0.3",
"base_model:quantized:TinyLlama/TinyLlama-1.1B-Chat-v0.3",
"text-generation-inference",
"4-bit",
"gptq",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 1,
"parameters_active_b": 1,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tinyllama-1.1b-chat-v0.3-gptq"
},
{
"slug": "prot_t5_xl_bfd",
"name": "Prot_T5_Xl_Bfd",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Rostlab/prot_t5_xl_bfd",
"description": "Open source model Rostlab/prot_t5_xl_bfd. 10 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 10,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"tf",
"t5",
"protein language model",
"dataset:BFD",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "prot_t5_xl_bfd"
},
{
"slug": "qwen3-4b-instruct-2507-unsloth-bnb-4bit",
"name": "Qwen3 4B Instruct 2507 Unsloth Bnb 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit",
"description": "Open source model unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit. 13 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 13,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"unsloth",
"conversational",
"arxiv:2505.09388",
"base_model:Qwen/Qwen3-4B-Instruct-2507",
"base_model:quantized:Qwen/Qwen3-4B-Instruct-2507",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-4b-instruct-2507-unsloth-bnb-4bit",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "phi-3.5-mini-instruct",
"name": "Phi 3.5 Mini Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/microsoft/Phi-3.5-mini-instruct",
"description": "Open source model microsoft/Phi-3.5-mini-instruct. 963 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 963,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"phi3",
"nlp",
"code",
"conversational",
"custom_code",
"multilingual",
"arxiv:2404.14219",
"arxiv:2407.13833",
"arxiv:2403.06412",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "phi-3.5-mini-instruct",
"logo_url": "/logos/phi.svg"
},
{
"slug": "meta-llama-3.1-8b-instruct-bnb-4bit",
"name": "Meta Llama 3.1 8B Instruct Bnb 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
"description": "Open source model unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit. 95 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 95,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"llama-3",
"meta",
"facebook",
"unsloth",
"conversational",
"en",
"arxiv:2204.05149",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:quantized:meta-llama/Llama-3.1-8B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3.1-8b-instruct-bnb-4bit",
"logo_url": "/logos/meta.svg"
},
{
"slug": "glm-4.7-flash-awq-4bit",
"name": "Glm 4.7 Flash Awq 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/cyankiwi/GLM-4.7-Flash-AWQ-4bit",
"description": "Open source model cyankiwi/GLM-4.7-Flash-AWQ-4bit. 43 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 43,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm4_moe_lite",
"conversational",
"en",
"zh",
"arxiv:2508.06471",
"base_model:zai-org/GLM-4.7-Flash",
"base_model:quantized:zai-org/GLM-4.7-Flash",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 3,
"context_window_tokens": 4096,
"parameters_total_b": 4,
"parameters_active_b": 4,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-4.7-flash-awq-4bit"
},
{
"slug": "dots.ocr",
"name": "Dots.Ocr",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/rednote-hilab/dots.ocr",
"description": "Open source model rednote-hilab/dots.ocr. 1243 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1243,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"dots_ocr",
"safetensors",
"image-to-text",
"ocr",
"document-parse",
"layout",
"table",
"formula",
"transformers",
"custom_code",
"image-text-to-text",
"conversational",
"en",
"zh",
"multilingual",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "dots.ocr"
},
{
"slug": "mistral-7b-bnb-4bit",
"name": "Mistral 7B Bnb 4Bit",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/mistral-7b-bnb-4bit",
"description": "Open source model unsloth/mistral-7b-bnb-4bit. 30 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 30,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"mistral",
"unsloth",
"mistral-7b",
"bnb",
"en",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "mistral-7b-bnb-4bit",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "glm-5-fp8",
"name": "Glm 5 Fp8",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/zai-org/GLM-5-FP8",
"description": "Open source model zai-org/GLM-5-FP8. 108 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 108,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"glm_moe_dsa",
"conversational",
"en",
"zh",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "glm-5-fp8"
},
{
"slug": "qwen-7b",
"name": "Qwen 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen-7B",
"description": "Open source model Qwen/Qwen-7B. 395 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 395,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen",
"custom_code",
"zh",
"en",
"arxiv:2309.16609",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen-7b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwq-32b-awq",
"name": "Qwq 32B Awq",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/QwQ-32B-AWQ",
"description": "Open source model Qwen/QwQ-32B-AWQ. 133 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 133,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"safetensors",
"qwen2",
"chat",
"conversational",
"en",
"arxiv:2309.00071",
"arxiv:2412.15115",
"base_model:Qwen/QwQ-32B",
"base_model:quantized:Qwen/QwQ-32B",
"4-bit",
"awq",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 22,
"context_window_tokens": 4096,
"parameters_total_b": 32,
"parameters_active_b": 32,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwq-32b-awq"
},
{
"slug": "deepseek-r1-distill-llama-70b",
"name": "Deepseek R1 Distill Llama 70B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
"description": "Open source model deepseek-ai/DeepSeek-R1-Distill-Llama-70B. 741 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 741,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"conversational",
"arxiv:2501.12948",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 49,
"context_window_tokens": 4096,
"parameters_total_b": 70,
"parameters_active_b": 70,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-r1-distill-llama-70b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "qwen2.5-coder-7b",
"name": "Qwen2.5 Coder 7B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B",
"description": "Open source model Qwen/Qwen2.5-Coder-7B. 134 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 134,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen2",
"code",
"qwen",
"qwen-coder",
"codeqwen",
"conversational",
"en",
"arxiv:2409.12186",
"arxiv:2309.00071",
"arxiv:2407.10671",
"base_model:Qwen/Qwen2.5-7B",
"base_model:finetune:Qwen/Qwen2.5-7B",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-coder-7b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "qwen2.5-3b",
"name": "Qwen2.5 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen2.5-3B",
"description": "Open source model Qwen/Qwen2.5-3B. 169 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 169,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"safetensors",
"qwen2",
"conversational",
"en",
"arxiv:2407.10671",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen2.5-3b",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-v2-lite-chat",
"name": "Deepseek V2 Lite Chat",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat",
"description": "Open source model deepseek-ai/DeepSeek-V2-Lite-Chat. 133 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 133,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v2",
"conversational",
"custom_code",
"arxiv:2405.04434",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-v2-lite-chat"
},
{
"slug": "tiny-qwen3forcausallm",
"name": "Tiny Qwen3Forcausallm",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/trl-internal-testing/tiny-Qwen3ForCausalLM",
"description": "Open source model trl-internal-testing/tiny-Qwen3ForCausalLM. 1 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1,
"language": "Python",
"license": "unknown",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"trl",
"conversational",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "tiny-qwen3forcausallm",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "deepseek-coder-v2-lite-instruct",
"name": "Deepseek Coder V2 Lite Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
"description": "Open source model deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. 539 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 539,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v2",
"conversational",
"custom_code",
"arxiv:2401.06066",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-coder-v2-lite-instruct"
},
{
"slug": "qwen3-0.6b-base",
"name": "Qwen3 0.6B Base",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen3-0.6B-Base",
"description": "Open source model Qwen/Qwen3-0.6B-Base. 146 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 146,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen3",
"conversational",
"arxiv:2505.09388",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 4,
"context_window_tokens": 4096,
"parameters_total_b": 6,
"parameters_active_b": 6,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen3-0.6b-base",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "diffractgpt_mistral_chemical_formula",
"name": "Diffractgpt_Mistral_Chemical_Formula",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/knc6/diffractgpt_mistral_chemical_formula",
"description": "Open source model knc6/diffractgpt_mistral_chemical_formula. 1 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"peft",
"safetensors",
"chemistry",
"text-generation-inference",
"atomgpt",
"diffraction",
"en",
"base_model:unsloth/mistral-7b-bnb-4bit",
"base_model:adapter:unsloth/mistral-7b-bnb-4bit",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "diffractgpt_mistral_chemical_formula",
"logo_url": "/logos/mistral.svg"
},
{
"slug": "qwen-7b-chat",
"name": "Qwen 7B Chat",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Qwen/Qwen-7B-Chat",
"description": "Open source model Qwen/Qwen-7B-Chat. 787 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 787,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"qwen",
"custom_code",
"zh",
"en",
"arxiv:2309.16609",
"arxiv:2305.08322",
"arxiv:2009.03300",
"arxiv:2305.05280",
"arxiv:2210.03629",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 5,
"context_window_tokens": 4096,
"parameters_total_b": 7,
"parameters_active_b": 7,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "qwen-7b-chat",
"logo_url": "/logos/qwen.svg"
},
{
"slug": "nvidia-nemotron-3-nano-30b-a3b-nvfp4",
"name": "Nvidia Nemotron 3 Nano 30B A3B Nvfp4",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4",
"description": "Open source model nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4. 100 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 100,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"nemotron_h",
"feature-extraction",
"nvidia",
"pytorch",
"conversational",
"custom_code",
"en",
"es",
"fr",
"de",
"ja",
"it",
"dataset:nvidia/Nemotron-Pretraining-Code-v1",
"dataset:nvidia/Nemotron-CC-v2",
"dataset:nvidia/Nemotron-Pretraining-SFT-v1",
"dataset:nvidia/Nemotron-CC-Math-v1",
"dataset:nvidia/Nemotron-Pretraining-Code-v2",
"dataset:nvidia/Nemotron-Pretraining-Specialized-v1",
"dataset:nvidia/Nemotron-CC-v2.1",
"dataset:nvidia/Nemotron-CC-Code-v1",
"dataset:nvidia/Nemotron-Pretraining-Dataset-sample",
"dataset:nvidia/Nemotron-Competitive-Programming-v1",
"dataset:nvidia/Nemotron-Math-v2",
"dataset:nvidia/Nemotron-Agentic-v1",
"dataset:nvidia/Nemotron-Math-Proofs-v1",
"dataset:nvidia/Nemotron-Instruction-Following-Chat-v1",
"dataset:nvidia/Nemotron-Science-v1",
"dataset:nvidia/Nemotron-3-Nano-RL-Training-Blend",
"arxiv:2512.20848",
"arxiv:2512.20856",
"arxiv:2601.20088",
"base_model:nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
"base_model:quantized:nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
"region:us"
],
"hardware_req": "24GB+ VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 21,
"context_window_tokens": 4096,
"parameters_total_b": 30,
"parameters_active_b": 30,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "nvidia-nemotron-3-nano-30b-a3b-nvfp4"
},
{
"slug": "falcon-h1-tiny-90m-instruct",
"name": "Falcon H1 Tiny 90M Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/tiiuae/Falcon-H1-Tiny-90M-Instruct",
"description": "Open source model tiiuae/Falcon-H1-Tiny-90M-Instruct. 31 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 31,
"language": "Python",
"license": "other",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"falcon_h1",
"falcon-h1",
"edge",
"conversational",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "falcon-h1-tiny-90m-instruct",
"logo_url": "/logos/falcon.svg"
},
{
"slug": "hermes-3-llama-3.2-3b",
"name": "Hermes 3 Llama 3.2 3B",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B",
"description": "Open source model NousResearch/Hermes-3-Llama-3.2-3B. 174 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 174,
"language": "Python",
"license": "llama3",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"Llama-3",
"instruct",
"finetune",
"chatml",
"gpt4",
"synthetic data",
"distillation",
"function calling",
"json mode",
"axolotl",
"roleplaying",
"chat",
"conversational",
"en",
"arxiv:2408.11857",
"text-generation-inference",
"endpoints_compatible",
"deploy:azure",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 2,
"context_window_tokens": 4096,
"parameters_total_b": 3,
"parameters_active_b": 3,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "hermes-3-llama-3.2-3b",
"logo_url": "/logos/meta.svg"
},
{
"slug": "meta-llama-3.1-8b-instruct",
"name": "Meta Llama 3.1 8B Instruct",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct",
"description": "Open source model unsloth/Meta-Llama-3.1-8B-Instruct. 94 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 94,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"llama-3",
"meta",
"facebook",
"unsloth",
"conversational",
"en",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:finetune:meta-llama/Llama-3.1-8B-Instruct",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3.1-8b-instruct",
"logo_url": "/logos/meta.svg"
},
{
"slug": "meta-llama-3.1-8b-instruct-gguf",
"name": "Meta Llama 3.1 8B Instruct Gguf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF",
"description": "Open source model bartowski/Meta-Llama-3.1-8B-Instruct-GGUF. 321 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 321,
"language": "Python",
"license": "llama3.1",
"tags": [
"AI",
"LLM",
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:quantized:meta-llama/Llama-3.1-8B-Instruct",
"endpoints_compatible",
"region:us",
"conversational"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 6,
"context_window_tokens": 4096,
"parameters_total_b": 8,
"parameters_active_b": 8,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "meta-llama-3.1-8b-instruct-gguf",
"logo_url": "/logos/meta.svg"
},
{
"slug": "deepseek-v3-0324",
"name": "Deepseek V3 0324",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324",
"description": "Open source model deepseek-ai/DeepSeek-V3-0324. 3087 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 3087,
"language": "Python",
"license": "mit",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"deepseek_v3",
"conversational",
"custom_code",
"arxiv:2412.19437",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"fp8",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "deepseek-v3-0324"
},
{
"slug": "elm",
"name": "Elm",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/Joaoffg/ELM",
"description": "Open source model Joaoffg/ELM. 2 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 2,
"language": "Python",
"license": "llama2",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"academic",
"university",
"en",
"nl",
"arxiv:2408.06931",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "elm"
},
{
"slug": "llama-2-13b-chat-hf",
"name": "Llama 2 13B Chat Hf",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/meta-llama/Llama-2-13b-chat-hf",
"description": "Open source model meta-llama/Llama-2-13b-chat-hf. 1109 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 1109,
"language": "Python",
"license": "llama2",
"tags": [
"AI",
"LLM",
"transformers",
"pytorch",
"safetensors",
"llama",
"facebook",
"meta",
"llama-2",
"conversational",
"en",
"arxiv:2307.09288",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "16GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 9,
"context_window_tokens": 4096,
"parameters_total_b": 13,
"parameters_active_b": 13,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "llama-2-13b-chat-hf",
"logo_url": "/logos/meta.svg"
},
{
"slug": "svara-tts-v1",
"name": "Svara Tts V1",
"category": "AI Models",
"is_open_source": true,
"website": "https://huggingface.co/kenpath/svara-tts-v1",
"description": "Open source model kenpath/svara-tts-v1. 18 likes on Hugging Face.",
"pros": [
"Open Source",
"Running Locally"
],
"cons": [
"Requires GPU"
],
"stars": 18,
"language": "Python",
"license": "apache-2.0",
"tags": [
"AI",
"LLM",
"transformers",
"safetensors",
"llama",
"text-to-speech",
"speech-synthesis",
"multilingual",
"indic",
"orpheus",
"lora",
"low-latency",
"gguf",
"zero-shot",
"emotions",
"discrete-audio-tokens",
"hi",
"bn",
"mr",
"te",
"kn",
"bho",
"mag",
"hne",
"mai",
"as",
"brx",
"doi",
"gu",
"ml",
"pa",
"ta",
"ne",
"sa",
"en",
"dataset:SYSPIN",
"dataset:RASA",
"dataset:IndicTTS",
"dataset:SPICOR",
"base_model:canopylabs/3b-hi-ft-research_release",
"base_model:adapter:canopylabs/3b-hi-ft-research_release",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"hardware_req": "8GB VRAM",
"hosting_type": "self-hosted",
"ai_metadata": {
"vram_inference_gb": 1,
"context_window_tokens": 4096,
"parameters_total_b": 0,
"parameters_active_b": 0,
"is_multimodal": false
},
"referral_url": "https://m.do.co/c/2ed27757a361",
"id": "svara-tts-v1"
},
{
"slug": "postman",
"name": "Postman",
"category": "API Development",
"is_open_source": false,
"pricing_model": "Freemium",
"website": "https://www.postman.com/",
"description": "An API platform for building and using APIs.",
"alternatives": [
"hoppscotch"
],
"tags": [
"API",
"Testing",
"Developer Tools"
],
"logo_url": "https://www.vectorlogo.zone/logos/getpostman/getpostman-icon.svg",
"avg_monthly_cost": 15,
"pros": [
"Comprehensive feature set for API development",
"Excellent collaboration tools",
"Extensive integrations with CI/CD"
],
"cons": [
"Can be resource-heavy and slow",
"Requires an account for core collaboration features",
"Some advanced features are locked behind expensive subscriptions"
]
},
{
"slug": "hoppscotch",
"name": "Hoppscotch",
"category": "API Development",
"is_open_source": true,
"pricing_model": "Free/Open Source",
"website": "https://hoppscotch.io/",
"description": "An open-source API development ecosystem.",
"github_repo": "hoppscotch/hoppscotch",
"alternatives": [
"postman"
],
"tags": [
"API",
"Testing",
"Developer Tools",
"Open Source"
],
"logo_url": "https://hoppscotch.io/_nuxt/logo.6d552ca3.svg",
"avg_monthly_cost": 0,
"pros": [
"Lightweight and runs directly in the browser",
"Fully open-source and self-hostable",
"Real-time collaboration and history syncing"
],
"cons": [
"Browser extensions sometimes required for certain requests",
"Fewer enterprise integrations compared to commercial alternatives"
]
},
{
"slug": "seaweedfs",
"name": "SeaweedFS",
"category": "Cloud Infrastructure",
"is_open_source": true,
"github_repo": "seaweedfs/seaweedfs",
"stars": 22000,
"website": "https://github.com/seaweedfs/seaweedfs",
"description": "SeaweedFS is a fast distributed storage system for blobs, objects, files, and data lake, for billions of files!",
"pros": [
"Extremely fast for small files",
"Highly scalable distributed architecture",
"S3 compatible API"
],
"cons": [
"More complex to configure than some alternatives"
],
"language": "Go",
"license": "Apache 2.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=github.com/seaweedfs",
"last_commit": "2025-03-01T00:00:00Z",
"hosting_type": "self-hosted",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/seaweedfs"
}
},
{
"slug": "ceph",
"name": "Ceph",
"category": "Cloud Infrastructure",
"is_open_source": true,
"github_repo": "ceph/ceph",
"stars": 13000,
"website": "https://ceph.io",
"description": "Ceph is a highly scalable distributed storage solution for block, object, and file storage.",
"pros": [
"Enterprise-grade reliability and scalability",
"Unified storage (block, object, file)",
"Strong community and industry support"
],
"cons": [
"Steep learning curve and complex management",
"Resource intensive"
],
"language": "C++",
"license": "LGPL-2.1",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=ceph.io",
"last_commit": "2025-03-01T00:00:00Z",
"hosting_type": "self-hosted",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/ceph"
}
},
{
"slug": "rustfs",
"name": "RustFS",
"category": "Cloud Infrastructure",
"is_open_source": true,
"github_repo": "rustfs/rustfs",
"stars": 1000,
"website": "https://rustfs.com/",
"description": "High-performance S3-compatible object storage designed for modern data workloads.",
"pros": [
"Written in Rust for high performance and safety",
"Permissive Apache 2.0 license",
"Faster than MinIO for small object workloads"
],
"cons": [
"Newer project with a smaller ecosystem",
"Less enterprise features than mature counterparts"
],
"language": "Rust",
"license": "Apache 2.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=rustfs.com",
"last_commit": "2025-02-15T00:00:00Z",
"hosting_type": "self-hosted",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/rustfs"
}
},
{
"slug": "forward-email",
"name": "Forward Email",
"category": "Email",
"is_open_source": true,
"github_repo": "forwardemail/forwardemail.net",
"stars": 1488,
"website": "https://forwardemail.net",
"description": "Privacy-focused encrypted email for everyone. All-in-one alternative to Gmail, Mailchimp, and Sendgrid with free inbound forwarding, full email hosting, built-in webmail, and IMAP/POP3/SMTP support.",
"pros": [
"100% open-source with self-hosted Docker deployment",
"Free inbound email forwarding for custom domains",
"Built-in webmail with IMAP/POP3/SMTP support",
"Quantum-resistant encryption for future-proof security"
],
"cons": [
"Self-hosting email requires careful DNS and deliverability setup",
"Native apps still in development"
],
"last_commit": "2026-03-02T16:45:21Z",
"language": "JavaScript",
"license": "MIT",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=forwardemail.net"
},
{
"slug": "gmail",
"name": "Gmail",
"category": "Email",
"is_open_source": false,
"pricing_model": "Paid/Freemium",
"website": "https://mail.google.com",
"description": "Google's free email service with 15GB storage, powerful search, and integration with Google Workspace.",
"alternatives": [
"forward-email"
],
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=gmail.com",
"avg_monthly_cost": 6,
"pros": [
"Excellent spam filtering and search",
"15GB free storage",
"Deep integration with Google Workspace",
"Works everywhere with great mobile apps"
],
"cons": [
"Google scans emails for ad targeting",
"No end-to-end encryption by default",
"Vendor lock-in with Google ecosystem",
"Privacy concerns for sensitive communications"
]
},
{
"slug": "tymeslot",
"name": "Tymeslot",
"category": "Productivity",
"is_open_source": true,
"github_repo": "Tymeslot/tymeslot",
"website": "https://github.com/Tymeslot/tymeslot",
"description": "Self-hostable, open-source meeting scheduling platform built with Elixir/Phoenix LiveView.",
"pros": [
"No ads, no tracking, no per-seat pricing",
"Google Calendar sync with timezone-aware scheduling",
"SSO support via OIDC/OAuth out of the box",
"Multiple calendar accounts per user"
],
"cons": [
"Smaller community and ecosystem than Calendly",
"Fewer third-party integrations out of the box"
],
"language": "Elixir",
"license": "AGPL-3.0",
"logo_url": "https://www.google.com/s2/favicons?sz=128&domain=raw.githubusercontent.com",
"deployment": {
"type": "docker-compose",
"local_path": "./.docker-deploy/tymeslot"
}
}
]
Reference in New Issue View Git Blame Copy Permalink