The local AI isn't responding — what now?
3 min · 4 steps
Settings → AI → Test active. If the model crashed, restart Ollama / reinstall.
The local SLM runs as a separate process (Ollama by default). Crashes happen — usually under memory pressure on lower-end machines.
Steps
- Check the StatusStrip at the bottom.
The Model lamp shows the active SLM's name + state. If it's red or says "unreachable", the runtime can't talk to it.
- Settings → AI → Test active.
Sends a tiny prompt. Errors surface inline with the underlying message (Ollama not running, model not pulled, OOM).
- Restart Ollama if needed.
On macOS: `brew services restart ollama` from a terminal. On Linux: `systemctl --user restart ollama`. On Windows: restart the Ollama tray app. Avery auto-reconnects within a few seconds.
- Re-install the variant if the file is corrupt.
Settings → AI → AI Model for Runtime → click the Active variant → 'Reinstall'. Pulls the model fresh from Ollama's registry.
Live recipes need the desktop
This article is a static preview. The in-app Help sidecar inside Avery NXR can fire each step against your live project — install the desktop to use it interactively.