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 community report says LM Studio 0.4.24 on Windows suffers a persistent inference slowdown after a Radeon 780M runs several Vulkan memory tests while a Gemma 4 model remains loaded. Generation reportedly fell from about 10 tokens per second to 8.75, and restarting LM Studio only partly recovered performance.

Why it matters

A full Windows restart restored the original speed. The reporter says the same workload did not slow an upstream llama.cpp build on the same machine, although the configurations differed. That makes this a useful troubleshooting lead, not proof that LM Studio or AMD’s driver is at fault. If you are testing local models on similar hardware, record performance before and after other Vulkan workloads and try a full restart before blaming the model. A graphics reset alone did not restore the reported baseline. Would you treat an 11% drop as a bug worth chasing, or an acceptable price for experimental local-AI plumbing?

Discuss: Would you treat an 11% drop as a bug worth chasing, or an acceptable price for experimental local-AI plumbing?

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.