Get Started
← AI on your own PC

llama.cpp

The engine under most local AI apps: runs language models fast on CPUs, graphics cards and Macs.

View verified repo ↗Learn to install it, freeNot tested by us yet

What you can do with it

  • Run open models as fast as your hardware allows
  • Serve a local OpenAI-style API
  • Fit bigger models on modest hardware with quantisation

Getting started

We haven’t written a step-by-step guide for this one yet. Our free mission shows you how to install any tool from GitHub safely, so you can try it today.

Start the free mission

More in AI on your own PC

Tested

Ollama

AI on your own PC

Run AI models like Qwen, Gemma and DeepSeek on your own computer, offline.

★ 182k/MIT/~10 min
Tested

Open WebUI

AI on your own PC

A clean ChatGPT-style interface for your local models.

★ 154k/See repo/~15 min
Tested

Argos Translate + LibreTranslate

AI on your own PC

Offline translation on your own computer: about 100 language models, a simple web app, and nothing uploaded.

★ 6.5k/MIT/~20 min