Skip to content

Quickstart

Run a model on your computer and chat with it in your browser.

Terminal window
curl -fsSL https://mistralrs.dev/install.sh | sh

Follow the installer, then open a new terminal.

Start a model:

Terminal window
mistralrs serve -m Qwen/Qwen3-4B --quant 4

When the server is ready, open http://localhost:1234/ui and send a message.

Keep the terminal open while you chat. Press Ctrl+C when you’re done.