unsloth repositories

Trending repositories tagged unsloth, ranked by trending score. Updated daily.

  1. 1
    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.

    GitHub · Python · 79,907 stars · 7,439 forks · +98 stars in 24 hours · Trending score 3.93

  2. 2
    AlexsJones/llmfit

    Hundreds of models & providers. One command to find what runs on your hardware.

    GitHub · Rust · 39,202 stars · 2,535 forks · +63 stars in 24 hours · Trending score 3.41

  3. 3
    unslothai/notebooks

    250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.

    GitHub · Jupyter Notebook · 5,810 stars · 973 forks · 0 stars in 24 hours · Trending score 1.14

  4. 4
    JuliusBrussee/cavegemma

    LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman

    GitHub · Python · 123 stars · 15 forks · 0 stars in 24 hours · Trending score 0.95

  5. 5
    billyrdavis1985-bot/hf-critic

    Fine-tuning open-source LLMs into reasoning-process critics — QLoRA, held-out eval, controlled cross-model comparison. Part of the IRMB program.

    GitHub · Python · 6 stars · 0 forks · +1 stars in 24 hours · Trending score 0.46

  6. 6
    sambuddha001/cyberqwen-2b

    Air-gapped 2B Cybersecurity SLM for vulnerability triage, CTFs, and payload analysis. Runs 100% offline on standard CPUs with Ollama, built-in WebUI & zero cloud cost.

    GitHub · Jupyter Notebook · 7 stars · 1 forks · +1 stars in 24 hours · Trending score 0.40

  7. 7
    nolabs-ai/deepfabric

    Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline

    GitHub · Python · 897 stars · 84 forks · 0 stars in 24 hours · Trending score 0.32

  8. 8
    T-Crypt/speculum

    monitor for a local LLM runtime (llama-swap, NInfer, Strata, more) -- metrics ported to berth.

    GitHub · Python · 15 stars · 0 forks · 0 stars in 24 hours · Trending score 0.22

  9. 9
    pnnnx/local-code-tutor

    Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, llama.cpp, LoRA weight analysis with charts

    GitHub · Python · 15 stars · 0 forks · 0 stars in 24 hours · Trending score 0.14

  10. 10
    endend2003-cmd/Tactical-Matrix-Console

    WarMatrix 2026: Next-Gen Tactical Simulation & AI Command Console

    GitHub · HTML · 118 stars · 0 forks · 0 stars in 24 hours · Trending score 0.06

  11. 11
    Keljian/JSE

    Local-first desktop assistant for the whole job hunt — scrape listings, match with a local LLM, generate applications in your own voice, and track everything on a Kanban board.

    GitHub · Python · 30 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    natedemoss/ladder

    Ladder: small open models fine-tuned for competitive programming. QLoRA training + verifiable eval that runs on Kaggle/Colab GPUs.

    GitHub · Python · 6 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  13. 13
    Mohamed-Elgaraihy/customer-service-ai-finetune

    Fine-tune the Qwen 2.5 AI model to act as a smart customer service assistant using Python and Unsloth on Google Colab.

    GitHub · Jupyter Notebook · 13 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00

  14. 14
    bemlerlabs/glm-5.3-flash-dgx-spark-dflash2

    A practical recipe for serving GLM-5.3-Flash (320B MoE) on a single 128GB NVIDIA DGX Spark with DFlash2 speculative decoding.

    GitHub · Shell · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  15. 15
    Weschera/GLM-5.3-Flash-Unsloth-1x-DGX-Spark

    GLM-5.3-Flash on ONE DGX Spark: Unsloth UD-IQ3_XXS + llama.cpp MTP. Spark Bench TrueScore 93.4 (thinking OFF) — beats our 2-Spark EXL3 TP2. Validated serve config, thinking-off template patch, full evidence.

    GitHub · Jinja · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  16. 16
    rugbedbugg/Phantasm

    Turn someone’s chat history into a chatbot that talks like them. Extract the personality, fine-tune it, and run the result locally. Uses Colab CLI and Pixeldrain for off-host model training and extraction

    GitHub · Python · 21 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00