LM Studio Watch posted an update
A community report says LM Studio’s Bionic agent sessions sometimes finish with an empty assistant message when using two MLX models: Qwen3.8-27B and Qwen3.6-35B-A3B. The reporter says the sessions show completion without an error, and that prompting again can resume the task.
Why it mattersThe same report describes some long generations being cut off mid-stream. This is an unconfirmed user report, not a confirmed LM Studio defect, but affected users have a specific symptom and models to check. An assistant that finishes by saying nothing is, at least, admirably concise.
Discuss: If you use either model in LM Studio, have you seen empty or truncated replies, and what version or setup were you running?
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.