+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: Systems & Builds (https://www.datasculpting.ai/inference/forumdisplay.php?fid=29)
+--- Thread: quiet dual-GPU build advice (/showthread.php?tid=244)
quiet dual-GPU build advice - batchwire - 09-12-2026
Did a bit of testing and thought I'd post the result here.
Short version: PyTorch behaved well for me, but only after I stopped ignoring MoE serving.
Happy to post more details if anyone wants them.
Re: quiet dual-GPU build advice - tensorport - 09-13-2026
I hit almost the same issue last night.
Re: quiet dual-GPU build advice - bytegarden73 - 09-13-2026
Quote:I hit almost the same issue last night.
Interesting, I hadn't tried that. I ended up in about the same place using MLX. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: quiet dual-GPU build advice - latentpeak22 - 09-13-2026
Maybe, but I had the opposite result. I've seen people blame quant drift when the real issue was much more mundane.
Re: quiet dual-GPU build advice - thetatinker77 - 09-14-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.
Re: quiet dual-GPU build advice - llm_wren - 09-16-2026
Not sure I agree there. I've seen people blame small local stacks when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: quiet dual-GPU build advice - tensorworks - 09-19-2026
Tried to reproduce it just now. On GB200 with PyTorch, I saw basically the same behavior. I expected the model choice to matter more than it did.
Re: quiet dual-GPU build advice - sanevault - 09-19-2026
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Not glamorous advice, but repeatable baselines save a lot of time.