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

Stop dividing the GRPO eval loss by the accumulation steps (#11337)
Vineeth Sai Varikuntla committed 2 months ago
06c1bb4
8a9ad3c
Studio: scale spacing with the UI font size (#11458)
Michael Han committed 2 months ago
10c380e
studio: copy full prompts from the api monitor (#11340)
Maheswar Kumar committed 2 months ago
a9feb95
461f5ab