+- 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 with LM Studio (/showthread.php?tid=1115)
LM Studio surprisingly handy with LM Studio - rocmmixer - 10-12-2026
Spent some time on this today and wanted to compare notes.
Two paths both seem viable, but they break down differently once workstation thermals becomes important.
Trying to avoid rebuilding the whole thing twice.
Re: LM Studio surprisingly handy with LM Studio - vectorcrate98 - 10-12-2026
Quote:Spent some time on this today and wanted to compare notes.
I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: LM Studio surprisingly handy with LM Studio - mintforge - 10-12-2026
Need a little more detail here. Is this local-only or are you routing anything externally?
Re: LM Studio surprisingly handy with LM Studio - vramarch - 10-12-2026
Need a little more detail here. Are you testing this on Threadripper box or something else?
Re: LM Studio surprisingly handy with LM Studio - orbitbench6 - 10-15-2026
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup. At this point the real bottleneck is my patience.
Re: LM Studio surprisingly handy with LM Studio - dockridge - 10-15-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.
Re: LM Studio surprisingly handy with LM Studio - vectorcrate98 - 10-16-2026
Good point. I don't think your conclusion is far off.
Re: LM Studio surprisingly handy with LM Studio - amberhall - 10-16-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: LM Studio surprisingly handy with LM Studio - oxidemixer - 10-16-2026
Quote:My first guess would be this: Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repe
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at reranking. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: LM Studio surprisingly handy with LM Studio - pixelspark - 10-16-2026
Good point. The pattern around quant drift has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.