2 Commits

Author	SHA1	Message	Date
jmorganca	582d93ab22	fix: lazy init MLX for quantization and improve library discovery ... - Add lazy MLX initialization in quantizeTensor to ensure the library is loaded when quantization is requested - Add exe-relative build path search for dev mode on macOS, so the ollama binary can find libmlxc.dylib in build/lib/ollama/ when running from the repo root	2026-01-17 22:46:20 -08:00
Patrick Devine	a077d996e3	Fix create and show commands for experimental models (#13741) ... * x: make `ollama create --experimental` import from safetensors This change allows pulling in safetensors models into the new experimental model format, and also fixes the `ollama show` command to be able to correctly display the model information. * gofumpt the linter * gofumpt the linter again * validate the model name	2026-01-16 14:31:55 -08:00