unslothai/unsloth

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Stars Over Time

68,960 stars by
wLv
PythonApache License 2.0agentdeepseekdeepseek-r1fine-tuninggemmagemma3gpt-ossllamallama3llmllmsmistralopenaiqwenqwen3reinforcement-learningtext-to-speechttsunslothvoice-cloning

Growth

HOT
Last 30 days+1191 stars

Owner

Notable Stargazers

Building unslothai/unsloth?

We track who's paying attention — companies, roles, and the developers most likely to contribute or adopt.

Get in touch