llama.cpp

ggml-org/llama.cpp

Run LLMs locally with minimal setup, maximum hardware support

What llama.cpp buries

Ollama#1 by stars

Run open-source LLMs locally on your own machine

MITupdated today

Multi-model AI desktop client with local-first privacy

AGPL-3.0updated today

LocalAI#3 by stars

Self-hosted AI runtime for text, voice, vision, and agents

MITupdated today

Jan#4 by stars

Run AI models locally or connect to cloud, privately

Custom licenseupdated today

5ire#5 by stars

Smart desktop AI assistant with powerful local knowledge features

Custom licenseupdated 1mo ago