curl -fsSL https://ollama.com/install.sh | shollama pull qwen3:32bdocker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:mainsudo tailscale serve --bg 8080- From Tailscale network:
http://YOUR_MACHINE_NAME:8080 - Chat interface like ChatGPT, no API calls needed