Run AI Locally: Ollama + Open WebUI

Run a ChatGPT-style assistant on your own computer, free and private. Ollama runs the models; Open WebUI gives you a chat page.

1. Install Ollama

Linux one-liner, or the installer from ollama.com for Mac and Windows.

curl -fsSL https://ollama.com/install.sh | sh

2. Run a model

Downloads it the first time, then opens a chat in the terminal.

ollama run llama3.2

3. Add a chat page

Run Open WebUI in Docker, connected to Ollama.

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data --name open-webui ghcr.io/open-webui/open-webui:main

4. Open it

Browse to http://localhost:3000, create the admin account and pick your model.

http://localhost:3000

FAQ

What hardware do I need?

Small models (3-8B parameters) run on 8-16 GB RAM; a GPU makes them much faster.

Is my data private?

Yes. Everything runs on your machine; nothing is sent to a cloud service.