Local AI Glossary

What is llama.cpp?

Source: local-llm.net/glossary

The foundational open-source inference engine for local AI, written in C/C++ by Georgi Gerganov. Supports GGUF models on CPU, NVIDIA GPU (CUDA), AMD GPU (ROCm), Apple GPU (Metal), and Vulkan. The engine that makes local AI portable and efficient across virtually any hardware.

How llama.cpp fits in the local AI stack

llama.cpp is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms