starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-17 22:54:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

update context length format.

Browse Source
This commit is contained in:
Maternion
2026-02-10 10:13:04 +05:30
committed by Jesse Gross
parent c980e19995
commit 2dbb000908
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/context-length.mdx
View File

@@ -6,9 +6,9 @@ Context length is the maximum number of tokens that the model has access to in m
<Note> <Note>
Ollama defaults to the following context lengths based on VRAM: Ollama defaults to the following context lengths based on VRAM:
- < 24 GiB VRAM: 4,096 context - < 24 GiB VRAM: 4k context
- 24-48 GiB VRAM: 32,768 context - 24-48 GiB VRAM: 32k context
- &gt;= 48 GiB VRAM: 262,144 context - &gt;= 48 GiB VRAM: 256k context
</Note> </Note>
Tasks which require large context like web search, agents, and coding tools should be set to at least 64000 tokens. Tasks which require large context like web search, agents, and coding tools should be set to at least 64000 tokens.