llama.cpp

129k GitHub starsggml-org/llama.cpp

LLM inference in C/C++

Building blocks

llama.cpp is made of parts you can use on their own in your project. Copy a prompt to have your AI assistant add one for you, and see the licence card for what you may do with them.

  • Read and write local AI model files

    Free to use, even in closed products

    A Python library for GGUF files, the format llama.cpp uses to run AI models on your own computer.

    Use it to build

    • Converting and inspecting local models
    • Model tooling and pipelines
    View code
    Technical details
    Name
    gguf
    What it is
    Code library
    How to use it
    Install it and use it
    Install
    pip install gguf
    Licence
    MIT License (read from gguf-py/LICENSE)

Comments

No comments yet. Be the first to share your thoughts.