Find tools › Open-source projects › Keep data private

ggml

Open-source project · by ggml-org

A low-level software engine that helps computers run artificial intelligence models using basic hardware.

For developersPopular

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Build custom machine learning engines in pure C and C++
  • Run quantized models on consumer processors and graphics cards
  • Embed machine learning execution directly into native desktop or web applications

How to start

  1. Clone the repository with git clone https://github.com/ggml-org/ggml and navigate into it.

  2. Create and move to a build directory using mkdir build && cd build.

  3. Configure the project with cmake ...

  4. Compile the binaries with cmake --build . --config Release -j 8.

Good to know. This is a low-level development library requiring C/C++ compilation, not a ready-to-run chatbot. Active development and core contributions are steered through llama.cpp.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-16

More detail

A portable, dependency-free C/C++ tensor library built to run machine learning models efficiently on CPUs and hardware accelerators.

Standard machine learning frameworks are bloated and difficult to embed in standalone applications. Reach for this low-level library when building custom inference engines or running compressed models across everyday consumer hardware.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-15. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map