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.

Recent spike this week

7d +0.55% +419 stars in 7d

30d Not tracked yet — first tracked 2026-09-02

90d Not tracked yet — first tracked 2026-09-02

75,497 → 77,107 stars since Sep 2

75,414 Stars 7,095 Forks 1,108 Open issues

Recent spike this week. Coverage includes a Hacker News discussion (385 points) on Dec 1 and a Hacker News discussion (132 points) on Dec 1.

Generated Oct 1, 2026

Timeline

💬 2 Hacker News discussions

HN Unsloth: 80% faster, 50% less memory, 0% accuracy loss Llama finetuning Dec 1, 2023 132 pts
HN Show HN: 80% faster, 50% less memory, 0% loss of accuracy Llama finetuning Dec 1, 2023 385 pts

View on GitHub ↗ Visit site ↗

agent ai chatgpt deepseek fine-tuning gemma image-generation llama llm llms openai python qwen reinforcement-learning self-hosted stable-diffusion text-to-speech tts ui unsloth