unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
Unsloth makes LLM fine-tuning dramatically faster and more memory-efficient, letting you train on a single consumer GPU with minimal code.
From the README
curl -fsSL https://unsloth.ai/install.sh | sh
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
unsloth has 75.3k stars on GitHub. It has been forked 6.8k times. unsloth is written mainly in Python. It has been in active development since 2023. unsloth is available under the Apache-2.0 license. Its main topics are agent, ai, chatgpt, deepseek.
Read the full guideWhat is unsloth?
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
Is unsloth open source?
unsloth is an open-source project. It is released under the Apache-2.0 license.
Is unsloth free?
Yes. unsloth is free and open source — you can use, modify and self-host it.
What license does unsloth use?
unsloth is available under the Apache-2.0 license.
What language is unsloth written in?
unsloth is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/unslothai-unsloth.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.