macOS says the app cannot be opened.
Current beta builds may not yet be notarized. Open System Settings → Privacy & Security, find the blocked ToshLLM launch and choose Open Anyway. Confirm that the DMG came from the official release before bypassing the warning.
The engine exits with an illegal instruction.
An illegal-instruction or SIGILL error usually means the processor lacks AVX2. Install the release whose filename includes noavx2. ToshLLM marks that variant internally so future update checks continue selecting the compatible package.
The model fails while loading.
- Stop any server or benchmark already using VRAM.
- Reduce context size to shrink the KV cache.
- Increase the VRAM reserve so macOS and Metal allocations have headroom.
- For MoE models, move more experts to the CPU.
- Try a smaller quantization or model if the file still cannot fit.
Change one setting at a time and review Logs after every attempt. The app translates common engine failures into guidance, while the complete log preserves the underlying message.
A client cannot connect.
- Confirm the server status is Running and verify its configured port. The default is 8080.
- On the same Mac, use
http://127.0.0.1:8080rather than a public URL. - If API-key protection is enabled, include
Authorization: Bearer …. - For another device, enable local-network discovery, allow the macOS network prompt and use the Mac's local address.
- Restart the server after changing its listener or security settings.
Bring evidence, not guesses.
When reporting a reproducible issue, include the ToshLLM version, Mac model, AMD GPU, macOS version, model filename, relevant settings and the smallest useful section of the log. Do not publish API keys, private paths or personal chat content.
Open a GitHub issue when the problem persists.