Find tools › Open-source projects › Keep data private

ollama

Open-source project · by ollama

A free app that runs AI chatbots on your own computer, so your chats stay private.

No codingVery popular

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Chat with an AI model without sending data online
  • Try open models like Gemma, Qwen or DeepSeek
  • Power other local AI apps with models on your computer

How to start

  1. Download and install Ollama from the official Ollama website.

  2. In a terminal, run ollama run gemma4 to download a model and start chatting.

  3. Start with smaller models if your computer has little memory.

Good to know. Local models are usually less capable than top cloud models, and larger ones need a lot of RAM or GPU memory. The quick-install command pipes a script from the internet into your shell; use the manual installer if you prefer to check first.

Before you install

  • Checked by a personWe read what it does before listing it.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

A desktop app and command-line tool that downloads open-weight AI models (Gemma, Qwen, DeepSeek, gpt-oss and others) and runs them on your own computer.

Use it when you want to chat with an AI model offline or privately, or give other apps a local model through its built-in API on localhost:11434. It can also launch tools like Claude Code or Codex pointed at a local model with ollama launch.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map