Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Home / Open Source Radar / Inference & Training / unsloth

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.

Stars79.7k
Forks7.4k
LanguagePython
LicenseApache-2.0

About this project

unsloth is an open-source inference and training project on GitHub: 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. It is infrastructure rather than a finished product: the layer that serves, quantises, trains or orchestrates models. It is maintained by unslothai and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged agent, ai, chatgpt, deepseek, fine-tuning, gemma, image-generation, llama, llm, llms, openai and python, which is a fair summary of what it covers. That generally means an API surface, batching and memory management, and often an OpenAI-compatible endpoint so existing clients keep working unchanged.

It is written mainly in Python and released under APACHE-2.0, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 17, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 79,671 stars; 7,439 forks; primary language Python; license APACHE-2.0; last commit on November 17, 2026; topics agent, ai, chatgpt, deepseek, fine-tuning, gemma.