Skip to content

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

Commits on main

5f56a28
Kill llama-server during Windows cleanup (#16458)
Daniel Hiltgen committed 5 months ago
3e1b4fe
llama.cpp version update (#16463)
Daniel Hiltgen committed 5 months ago
52196f1
models: add support for gemma4-12b (#16457)
Patrick Devine committed 5 months ago
50bbda5
fix laguna patch build breakage (#16445)
Daniel Hiltgen committed 5 months ago
4b5bdd3
llm: ignore llama-server SSE ping comments (#16443)
Daniel Hiltgen committed 5 months ago
e828061
docs: configure hermes desktop app (#16440)
Bruce MacDonald committed 5 months ago
7a2073d
launch: isolate Codex launch configuration (#16437)
Parth Sareen committed 5 months ago
f57d111
llama.cpp version update (#16426)
Daniel Hiltgen committed 5 months ago
c34a79a
More harden app markdown URL handling (#16436)
Daniel Hiltgen committed 5 months ago
b051c9c
llm: detect llama-server load stalls from output (#16427)
Daniel Hiltgen committed 5 months ago
b7b7fa0
discover: allow Radeon 8060S iGPU by default (#16429)
Daniel Hiltgen committed 5 months ago
4c07681
Harden app markdown URL handling (#16380)
Daniel Hiltgen committed 5 months ago
6780f04
35fa277
launch: fix opencode local model limits (#16425)
Daniel Hiltgen committed 5 months ago
05747b0
4e807fd
log template details to aid troubleshooting (#16403)
Daniel Hiltgen committed 5 months ago
7d3a6c3
launch: migrate Codex config (#16397)
Parth Sareen committed 5 months ago
2c71d8d
launch: avoid legacy Codex App profiles (#16364)
ZiTian Zhao committed 5 months ago
5e9636f
llama-server followups (#16353)
Daniel Hiltgen committed 5 months ago
6308826
convert: fixes for qwen3next model conversion (#16354)
Patrick Devine committed 5 months ago
0e93ccc
e7766a4
mlx: fix dev mode search path (#16355)
Daniel Hiltgen committed 5 months ago
11be8f6
mlx: fix reported information in `ollama show` (#16289)
Patrick Devine committed 6 months ago
f63eea3