# llama.cpp

**Licence:** MIT  |  **Language:** C++  |  **Source:** https://github.com/ggml-org/llama.cpp

## Role in the stack

Direct GGUF inference engine

## Why it's here

The lowest-level way to run quantised GGUF models. Use it when you want full control over context, quantisation and sampling.

## Using it

See the project README in the fetched source:

```bash
./fetch-sources.sh ./sources
tar xzf ./sources/llama.cpp.tar.gz -C ./sources
```

This component is a library, not a service - install it into your own application environment.