llama.cpp
Software that runs AI models on your machine. Many local chat applications use it behind the scenes.
The fuller definition
llama.cpp is an open-source project for inference with supported language models across a range of hardware backends, commonly using GGUF model files.
- Model file
Compatible GGUF
- Runtime
llama.cpp implementation
- Backend
Selected hardware execution
A simplified relationship, not a screenshot or a complete design.
A concrete example
A compatible model is run with a command-line tool or served through the project's server facilities.
The distinction that matters
Despite its name, support is not limited to the original Llama family; check current model and hardware compatibility.
Related terms
GGUF
The file format most local AI applications use for downloaded models.
Hardware & hostingLocal model
A model that runs on your own computer, so your documents never leave it.
Hardware & hostingCPU — Central processing unit
The main brain of a computer. It can run AI models, but slowly.
Where it is taught
Choose an AI tool around the work productSource and further reading
ggml-org · llama.cppThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.