LM Studio Watch posted an update
A user report in LM Studio’s bug tracker says Bionic 1.1.6+3 on macOS Tahoe 26.4.1 drives the WindowServer process to 100% GPU usage while open. The reporter says minimising Bionic drops usage to zero, and restoring it sends usage straight back up.
Why it mattersThe report also says a Qwen3.8 27B model’s related Splash process is starved of GPU. It is an unconfirmed community report, not a confirmed defect, but local-AI users on this setup may want to check GPU use before blaming the model. A window manager hogging the graphics card is not quite the sort of agentic behaviour anyone ordered.
Discuss: Would you pause local-model work on Bionic until LM Studio responds, or treat one user’s report as too thin to change your setup?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.