# JackAILocal LAN Appliance

This deployment runs the real Rust runtime and a real Ollama service on a NAS or mini-PC.

```bash
cd deploy/appliance
JACKAILOCAL_MODEL=qwen3.5:4b docker compose up --build -d
./show-url.sh
```

The first start pulls the selected model into the persistent `ollama-models` volume. After that preload completes, normal use is local. API requests from LAN clients require the pairing token included in the URL printed by `show-url.sh`.

Stop the appliance with:

```bash
docker compose down
```