+- 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 (/showthread.php?tid=359)
Pages:
1
2
LM Studio surprisingly handy - cacheworks - 09-20-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on GB200, I ended up with decent performance, but the setup only really made sense once I adjusted around workstation thermals.
Nothing scientific here, just practical notes from a real setup.
Re: LM Studio surprisingly handy - oxidemixer - 09-21-2026
I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: LM Studio surprisingly handy - ggufwire22 - 09-21-2026
Good point. The pattern around embeddings 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 - prompttinker44 - 09-22-2026
Quote:Good point. The pattern around embeddings has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one mo
I tested this tonight. On mini PC with vLLM, I saw basically the same behavior. I expected the model choice to matter more than it did.
Re: LM Studio surprisingly handy - vectorcrate98 - 09-25-2026
Quote:[quote]Good point. The pattern around embeddings has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.
Re: LM Studio surprisingly handy - fusedhall - 09-25-2026
Quote:[quote][quote]Good point. The pattern around embeddings has been pretty similar for me. The biggest change for me was simplifying the stack instead of
I'd approach it in a boring order. On Threadripper box, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.
Re: LM Studio surprisingly handy - routerunner - 09-25-2026
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Phi and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: LM Studio surprisingly handy - vectorcrate98 - 09-25-2026
A couple questions before I guess too hard. What model, what runtime, and roughly what context size?
Re: LM Studio surprisingly handy - vectorshed43 - 09-25-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: LM Studio surprisingly handy - latentscope35 - 09-25-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.