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.

Add GGUF fit-target control and wire to llama-server --fit-target (#4882)

Mithilesh Kumarbb697682f69f