LM Studio Watch posted an update
A developer using LM Studio wants API requests to use one specific, already-loaded model instance, or fail without switching models or loading another one. The request is on LM Studio’s community issue tracker and is not a confirmed product fault or promised change.
Why it mattersThe developer says they are avoiding inference tests until they understand how model selection and automatic loading behave, because their application runs on a memory-constrained machine. It is a narrow but practical question for anyone building local-model tools: can a request be guaranteed to reach the model its caller specified?
Discuss: For local-model APIs, should exact model-instance selection be a default guarantee, or is explicit control over fallback and automatic loading enough?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.