Claude Code + qwen

(Back to the choices.)

qwen needs 32 GB of memory and about 25 GB of free disk space. You don’t need a Claude account.

Install Ollama, qwen, and Claude Code. Paste the block into PowerShell (Windows) or Terminal (Mac). The model download takes a while.

On Windows:

irm https://ollama.com/install.ps1 | iex
ollama pull qwen3-coder:30b
irm https://claude.ai/install.ps1 | iex

On Mac:

curl -fsSL https://ollama.com/install.sh | sh
ollama pull qwen3-coder:30b
curl -fsSL https://claude.ai/install.sh | bash

(It may ask for your Mac password; the typing doesn’t show.)

If the installer prints a command that adds a folder to your PATH, run that command too.

Set the context length. Click the Ollama icon (in the menu bar on a Mac, or the system tray on Windows) > Settings, and move the Context length slider to 64k.

Check. Open a new terminal window and run

ollama launch claude --model qwen3-coder:30b --yes -- -p "Reply with only the word hello."

It should print hello. (It can take a minute or two.)

Then run ollama ps and make sure the CONTEXT column says 65536. Then go to A First Example.

If you get stuck, copy the command and everything it printed and send it to Bryson or me.