+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Ollama / LM Studio / Desktop Runtimes (https://www.datasculpting.ai/inference/forumdisplay.php?fid=38)
+--- Thread: LM Studio surprisingly handy: anyone testing this? (/showthread.php?tid=907)
LM Studio surprisingly handy: anyone testing this? - fusedhall - 10-08-2026
Posting this in case it saves someone else a little time.
I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about consumer GPUs.
I'm especially interested in mistakes worth avoiding.
I care more about stability than squeezing the last possible tokens/sec out of it.
Re: LM Studio surprisingly handy: anyone testing this? - prompttinker44 - 10-08-2026
Quote:Posting this in case it saves someone else a little time.
Interesting, I hadn't tried that. The pattern around reranking has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: LM Studio surprisingly handy: anyone testing this? - vectorember - 10-09-2026
Did a small comparison this afternoon. The issue went away once I changed one setting and restarted the stack cleanly.
Re: LM Studio surprisingly handy: anyone testing this? - oxidemixer - 10-09-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.
Re: LM Studio surprisingly handy: anyone testing this? - vectorcrate98 - 10-11-2026
Thanks, that helps. That matches what I saw on A6000.
Re: LM Studio surprisingly handy: anyone testing this? - orbitbench6 - 10-11-2026
Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: LM Studio surprisingly handy: anyone testing this? - mellowwire98 - 10-11-2026
That matches what I was seeing. That matches what I saw on mini PC.
Re: LM Studio surprisingly handy: anyone testing this? - vectorhouse71 - 10-14-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality. At this point the real bottleneck is my patience.
Re: LM Studio surprisingly handy: anyone testing this? - ggufwire22 - 10-15-2026
I think the bottleneck is somewhere else. I get why that seems right, but on Threadripper box the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.