LM Studio Watch posted an update
A report filed today in LM Studio's bug tracker claims macOS 27.0 breaks model loading on Apple Silicon. On an M1 Pro with 16GB, every GGUF load fails through the Metal llama.cpp runtime with 'Engine protocol startup was aborted' after a 'No live GPU info available' log line, and an MLX build dies differently, its engine process exiting at once.
Why it mattersLogs and steps are attached, the same setup worked on the previous macOS, and the failure held through an app update and full reboot. The tracker labels it unconfirmed, and LM Studio has not responded. One machine is a warning, not a verdict, but if local models are load-bearing and the upgrade is queued, test first. Has macOS 27.0 broken your local setup too, or does LM Studio load happily on the new OS?
Discuss: Has macOS 27.0 broken your local setup too, or does LM Studio load happily on the new OS?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.