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

Fail closed when Studio exposure prompt is aborted (#10638)
Wasim Yousef Said committed 2 months ago
c10bff8
Fix Q-GaLore quantization of single-sign groups (#10841)
Vineeth Sai Varikuntla committed 2 months ago
3bdb5a4
Name the method on the uploaded model card (#10816)
Vineeth Sai Varikuntla committed 2 months ago
d4de144
Stop clean_text deleting every non-ASCII character (#10741)
Vineeth Sai Varikuntla committed 2 months ago
d49efcf