Port of Facebook's LLaMA model in C/C++

About llama.cpp

Inference of LLaMA model in pure C/C++. The main goal is to run the model using 4-bit quantization on a MacBook.

Supported platforms:

  • Mac OS
  • Linux
  • Windows (via CMake)
  • Docker

Supported models:

  • LLaMA ūü¶ô
  • Alpaca
  • GPT4All
  • Chinese LLaMA / Alpaca
  • Vigogne (French)
  • Vicuna

Ready to start building?

At Apideck we're building the world's biggest API network. Discover and integrate over 12,000 APIs.

Check out the API Tracker