Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

docs: update quickstart for tui (#14208)
Bruce MacDonald committed 9 months ago
bd6697a
cmd/tui: improve model picker UX (#14209)
Parth Sareen committed 9 months ago
77ba940
cmd: TUI UX improvements (#14198)
Parth Sareen committed 9 months ago
f08427c
update context length format.
Maternion committed 9 months ago
2dbb000
c980e19
Update context-length.mdx
Maternion committed 9 months ago
6162374
Add MLX runner with GLM4-MoE-Lite model support (#14185)
Patrick Devine committed 9 months ago
44bdd9a
docs: integration overview (#13831)
Bruce MacDonald committed 9 months ago
75695f1
safetensors quantization for mlx (#14184)
Patrick Devine committed 9 months ago
a0407d0
cmd: ollama launch pi (#14084)
Parth Sareen committed 9 months ago
5ef04da
win: add curl-style install script (#14178)
Daniel Hiltgen committed 9 months ago
aea316f
cmd: ollama menu and launch improvements (#14038)
Patrick Devine committed 9 months ago
235ba3d
build: fix Dockerfile mlx directory (#14131)
Jeffrey Morgan committed 9 months ago
099a0f1
docs: increased RAM requirement for parallelism
Richard Lyons committed 9 months ago
fff696e
anthropic: do not count image tokens for now (#14127)
Jeffrey Morgan committed 9 months ago
2e3ce6e
814630c
cmd: set claude code env vars on launch (#14109)
Parth Sareen committed 9 months ago
87cf187
chore: move x/mlxrunner into x/imagegen (#14100)
Michael Yang committed 9 months ago
6ddd886
move tokenizers to separate package (#13825)
Michael Yang committed 9 months ago
f137319
8a4b77f
cmd: ollama launch improvements (#14099)
Parth Sareen committed 9 months ago
5f53fe7
scripts: add macOS support to install.sh (#14060)
Bruce MacDonald committed 9 months ago
7ab4ca0
scheduler: default parallel=1 for qwen3next/lfm (#14103)
Jeffrey Morgan committed 9 months ago
e36f389