GStars
    unslothai

    unslothai/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.

    ai-agents
    llm
    ai
    self-hosted
    agent
    chatgpt
    deepseek
    fine-tuning
    gemma
    Python
    Apache-2.0
    79.1K stars
    7.4K forks
    379 GitHub watchers
    Updated Nov 6, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest 1 day ago, with 433 contributors on GitHub.

    Peaked at #12 in the weekly ranking the week of Apr 5, its best in the past year.

    Use Cases & Benefits

    • Provides a local UI and toolkit to run, train, and fine-tune large language models and diffusion models efficiently.
    • Delivers significantly faster training speeds and up to 80% less VRAM usage with exact accuracy and broad model support.
    • Use for fine-tuning large transformer models like Llama, Gemma, and Qwen on limited GPU resources with easy-to-use notebooks.
    • Use for developing and deploying multimodal AI applications including text-to-speech, speech-to-text, and image generation workflows.
    • Use for experimenting with reinforcement learning techniques such as DPO, GRPO, and PPO on custom datasets with optimized training pipelines.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Notebooks are beginner friendly. Read our guide. Add your dataset, click "Run All", and export your finetuned model to GGUF, Ollama, vLLM or Hugging Face.

    For Windows install instructions, see here.

    Excerpt from the unslothai/unsloth README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Aug 13: +370Aug 14: +459Aug 15: +505Aug 16: +509Aug 17: +677Aug 18: +427Aug 19: +269Aug 20: +255Aug 27: +120Aug 28: +75Aug 29: +98Aug 30: +94Aug 31: +93Sep 1: +85Sep 2: +59Sep 3: +68Sep 4: +55Sep 5: +57Sep 6: +47Sep 7: +45Sep 8: +73Sep 9: +110Sep 10: +47Sep 11: +34Sep 12: +20Sep 19: +62Sep 20: +20Oct 10: +41

    +8,505 stars over 86 days across 36 snapshot days; best day +677 on Aug 17.

    Forks

    7.4K+990

    Open issues

    479-618

    Compared with peers in AI Agents

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    unslothai/unsloth compared with AI Agents repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    morluto/rea450.0K+22.9K7516 days ago
    vercel-labs/agent-desktop21.4K+8.7K755 days ago
    milind-soni/OpenMausBot20.6K+8.4K75today
    stablyai/orca121.4K+6.7K75today
    thedotmack/claude-mem115.8K+4.7K75today
    unslothai/unsloth79.1K—651 day ago
    Category median115.8K+8.4K75—
    Compare unsloth with rea, agent-desktop, OpenMausBot →

    Discover Repositories

    Search across tracked repositories by name or description