Run Free Local AI on Windows in Under 10 Minutes

What You Need

Pick the Right Model for Your GPU

The model you run depends on your GPU's VRAM. Here's exactly what to use:

💡 Most people start with 8GB and qwen3-vl:8b. It's fast, capable, and handles images too.

1 Download & Install Ollama

Ollama is the engine that runs AI models locally. It handles everything under the hood.

1. Go to ollama.com/download
2. Click Download for Windows
3. Run the installer — click through and let it install
4. Ollama will open automatically when done

2 Install Docker Desktop

Docker runs the Open WebUI interface — the beautiful chat UI you'll actually talk to.

1. Go to docker.com/products/docker-desktop
2. Download and install Docker Desktop for Windows
3. Restart your PC if prompted
4. Open Docker Desktop and make sure it's running (whale icon in system tray)

3 Launch Open WebUI

Open PowerShell as Administrator and run this single command:

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

Then open your browser and go to:

4 Create Your Account & Pick a Model

1. Click Sign Up to create a local admin account (stays on your machine)
2. Once logged in, click the model dropdown at the top
3. Search for your model (e.g. qwen3-vl:8b) and click to download it
4. Wait for the download to complete — then start chatting!

5 Enable Persistent Memory

Make your AI remember things between conversations — just like Claude or ChatGPT with memory enabled.

1. Click your profile icon (top right)
2. Go to Settings → Personalization
3. Toggle on Memory (Experimental)

Now you can tell it things like "commit this to your memory" or "remember my preferences" and it will persist across sessions.

All Commands & Links