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

Restore full-rank gradients after Q-GaLore updates (#10878)
Vineeth Sai Varikuntla committed 1 month ago
48ab67f
Treat {{ and }} in a merged prompt as literal braces (#10742)
Vineeth Sai Varikuntla committed 1 month ago
fc84dd1
49b2ff9