Skip to main content
Back to Store

llama.cpp

Developmentv1.0.0

Foundational C/C++ local LLM runtime used by many tools for GGUF models.

No cost to useFree

Platform / OS

macOSWindows🐧Linux
macoswindowslinux
#ai-software#free-ai-software#local-ai#llm-runtime#gguf#inference
External project · free link · not sold by AILoft

llama.cpp is the foundational local inference project for LLaMA-like and GGUF models on CPUs, GPUs and Apple Silicon. Many desktop tools, servers and wrappers build on it thanks to its portability, speed and broad support. It is more of a developer runtime than a finished app, but it is key to the local AI ecosystem.