← All projects
AI

Ollama

Run powerful AI models entirely on your own computer.

Needs command lineFreemacOS · Windows · Linux★ 186,900 Free local AIPrivacyAI chat

Ollama lets you download and run large language models on your local machine. You can chat with models directly from your terminal or connect them to desktop and web apps. Everything runs on your hardware, keeping your conversations private.

✓ Good for

Anyone wanting to run AI models locally for total privacy.

✕ Skip it if

People who only want a standard browser chat like ChatGPT.

How to start

  1. Download installer for Mac, Windows, or Linux.
  2. Open your terminal and type ollama.
  3. Run ollama run gemma4 to chat.

Requires using the command line to start and download models.

Get it →GitHub repo

Not sure how to install, or if it’s safe? Read the beginner guide

FAQ

Is Ollama free?

Yes, Ollama is completely free and open-source under the MIT license, requiring no API keys or subscriptions to run local models.

Is Ollama safe to download?

It is open source (MIT license) with 186,900 GitHub stars, last updated 2026-11-14. Download only from the official link on this page, and scan the file before installing: see the safety checklist in our beginner guide.

Does Ollama work offline?

Yes, once you download your chosen models, Ollama runs entirely on your local hardware without needing an internet connection.

Compiled from the project README. 186,900 GitHub stars (2026-11-13) · License MIT · Last update 2026-11-14