Open Source Project Advanced

llama.cpp Inference Engine

ggerganov

LevelAdvanced

Who it's forDevelopers wanting efficient inference on low-spec machines

LanguageEnglish

PriceFree

TypeOpen Source Project

CategoryDeployment & Serving

Link check2026-10-18

Overview

A pure C/C++ inference engine that runs LLMs even on CPU — one of the de facto standards for local deployment.

Inference EngineLocal Deployment

https://github.com/ggerganov/llama.cpp