llama.cpp
Software
Inference
Active
The C++ project that put LLMs on laptops — and invented GGUF.
You're looking at a software record: a tool or platform in the AI stack — who maintains it and what hardware it runs on.
Georgi Gerganov's llama.cpp runs quantized open models on ordinary CPUs, Macs and small GPUs; its GGUF format became the standard for local model distribution. It is the foundation of the local-AI movement and the engine inside Ollama.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.