llama.cpp
llama.cpp is free software that runs large AI language models directly on a computer, using its own processor or graphics card. It is aimed mainly at programmers and technically inclined users who want to run AI models locally or on servers.
How hard it is to start using it. Easy: install it like a normal app, or use it in your browser. Advanced: you run it on your own server, use the command line, or it is a tool for developers.
Features
No commands neededSetup uses terminal commands; then runs via command-line tools
SourcePartly
Built-in model downloadsDownload by typing a model name or link
SourcePartly
Windows, Mac and Linux appPre-built binaries for computers; no clear app for all three
SourcePartly
Connects to your other toolsHas an OpenAI-compatible API server, no ready app connections
SourcePartly
Screenshots2
Listed in
Runs models locally, but it is a command-line and server tool, not a polished consumer app.
How to help
AI contributionsNot stated
The project has not said how it feels about AI-written contributions. Maintainers can set this by claiming the listing.