Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
docs: fix openapi schema for /api/ps and /api/tags endpoints (#14210)
f8dc7c9 SamareshSingh committed 9 months ago
bug: fix loading non-mlx models when ollama is built with mlx support (#14211)
4a37411 Patrick Devine committed 9 months ago
feature: add ctrl-g to allow users to use an editor to edit their prompt (#14197)
0aaf611 Patrick Devine committed 9 months ago
Add MLX runner with GLM4-MoE-Lite model support (#14185)
44bdd9a Patrick Devine committed 9 months ago
cmd: make 'ollama login' and 'ollama logout' aliases for 'ollama signin' and 'ollama signout' respectively (#14144)
9ec733e Jeffrey Morgan committed 9 months ago
cmd/config: offer to pull missing models instead of erroring (#14113)
9e2003f Parth Sareen committed 9 months ago
cmd: fix context limits for droid and add qwen3-coder-next ctx (#14112)
42e1d49 Parth Sareen committed 9 months ago
Revert "move tokenizers to separate package (#13825)" (#14111)
814630c Michael Yang committed 9 months ago
cmd: set context limits for cloud models in opencode (#14107)
8a4b77f Parth Sareen committed 9 months ago
scheduler: default parallel=1 for qwen3next/lfm (#14103)
e36f389 Jeffrey Morgan committed 9 months ago