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.
- Recommended by
- 2
- GitHub stars
- 79k
- Licence
- Apache-2.0
- Language
- Python
- Last commit
- 2 Nov 2026
What people said
“Unsloth: 80% faster, 50% less memory, 0% accuracy loss Llama finetuning (132 points)”
“Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning (385 points)”
Not software, abandoned or listed by mistake? Report this listing