Skip to content

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

Commits on main

2d9671d
desktop: add interface scaling setting (#9666)
Maheswar Kumar committed 2 months ago
8bc5530
docker publish: drop the build caches (#10959)
Daniel Han committed 2 months ago
dff8cb3
a97afe9
d584692
c2bfd21
8018196
Studio: run the formatter on llama_cpp.py (#10926)
Daniel Han committed 2 months ago
a6cf596