// Train & fine-tune
unslothv0.1.902-beta
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Open source Maintained For developers
IN ONE PARAGRAPH
unsloth is local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Good for: Developers and teams who want to train & fine-tune.
01How to start
- 1Read the official quick-start (link above).
- 2Install from the official package registry:
pip install unsloth - 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → LlamaFactory Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) ★ 76k transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ★ 168k ms-swift Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025). ★ 16k ART Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more! ★ 11k distilabel Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers. ★ 3.4k
03Related
Versions, why it is listed, for AI to read
Recent releases
- v0.1.902-beta 2026-10-01
- v0.1.900-beta 2026-09-28
- v0.1.815-beta 2026-09-23
- v0.1.814-beta 2026-09-22
- v0.1.813-beta 2026-09-22
For AI agents
- Interfaces：SDK
- Machine-readable record：/api/v1/software/unsloth.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22