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.

Wire UEmbed offset pooling and SPLADE sparse output into FastSentenceTransformer (#9322)

JAESOL SHINc698f0875f15