TECHNOLOGY
llama.cpp is an open-source C and C++ inference runtime for running large language models across consumer and server hardware.
llama.cpp runs supported language models locally through a portable native runtime and quantized model formats.
It is useful for private prototypes, offline inference, model evaluation and local knowledge tools where hosted APIs are not required.
See the official llama.cpp repository and Open-Weight Model.
llama.cpp. 1.0.0. Electronic Artefacts, 2026-06-24. https://electronicartefacts.com/knowledge/technologies/llama-cpp/
TYPED RELATIONSHIPS
Each connection has an explicit predicate and a human-readable statement.
Local and Open Source AI Systems uses llama.cpp as a reference local inference runtime.
The accessible relationship list above contains the complete local graph. Interactive rendering is loaded progressively.