LM Studio Watch posted an update
An LM Studio user on macOS 15.6.1 reports that models stopped loading in LM Studio 0.4.26, with the error “failed to initialize MTL0 backend”. The user says the problem occurs with Metal llama.cpp v2.66.0 on an Apple M1 Max.
Why it mattersTheir workaround is specific: in Settings, open Runtime, then Runtime Selections, and choose Metal llama.cpp v2.65.1 for GGUF. They report that models then load and work normally. This is one user’s report on LM Studio’s community tracker, not a confirmed wider fault. But for affected local-model users, it offers a practical version to try while the cause is investigated.
Discuss: Should LM Studio make it easier to roll back a runtime when an update stops local models loading, or is choosing an older version an acceptable workaround?
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.