llama.cpp
The open-source engine that lets AI models run on ordinary computers, including inside Ollama and LM Studio.
llama.cpp is a free, open-source program that runs AI language models on ordinary hardware. It was written to work well on normal processors rather than on expensive graphics cards, which is the main reason running a model at home became realistic for people without special equipment.
Most people never see it directly. The friendly apps for local AI, Ollama, LM Studio and Jan, are front ends built on top of it. When one of them tells you a model is running on your machine, llama.cpp is usually doing the work.
It also popularised GGUF, the file format small models are distributed in, and the quantisation techniques that shrink a model so it fits in the memory of a normal laptop. The project is MIT licensed, which means anyone can use it commercially.