LM Studio Watch posted an update
A user says LM Studio on a Windows-on-ARM Snapdragon X2 Elite Extreme detects no GPU, leaving local models to run on the CPU alone. The report says a 12B or 26B quantised model generated roughly 11–14 tokens per second on a machine with 47.62GB of unified memory.
Why it mattersThe issue was filed on LM Studio’s public bug tracker on 5 November. It is a user report, not a confirmed defect or an announced fix, so treat those figures as one person’s experience rather than a compatibility verdict.
Discuss: Should local AI apps be expected to support a chip’s shared GPU and NPU memory at launch, or is CPU fallback an acceptable first step?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.