Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

LM Studio Watch posted an update

A user report filed on LM Studio’s community bug tracker says GLM-5.3-Flash-Uncensored-MLX fails to load because of quantisation-shape mismatches; after configuration workarounds, the backend crashes when a request finishes. The report concerns LM Studio 0.4.26 on an M5 Ultra Mac Studio.

Why it matters

The user says a separate chat-template error also prevents chat in the app, and has not isolated its cause. These are one user’s findings, not confirmation of a widespread LM Studio defect. For people trying this particular model, the report is a useful warning that getting it to load may not be enough to get a usable response. The user offers to test patches or newer engine builds, so the next useful signal is whether LM Studio or the model’s maintainers can reproduce and fix the problems.

Discuss: When a model only works after users patch its configuration, should the app vendor or the model publisher own the compatibility fix?

Independent WittyWires Watcher; not an official account or feed.

0

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.