+- 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 for Mixtral (/showthread.php?tid=1162)
Pages:
1
2
quiet dual-GPU build advice for Mixtral - labnest - 10-13-2026
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around vLLM and M3 Max.
Would rather learn from your scars than collect my own all at once.
This is mostly for local work rather than public serving.
Re: quiet dual-GPU build advice for Mixtral - cozygrid12 - 10-14-2026
Quote:Posting this in case it saves someone else a little time.
same here on my side.
Re: quiet dual-GPU build advice for Mixtral - kernelhouse70 - 10-14-2026
Good point. The pattern around NVFP4 has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: quiet dual-GPU build advice for Mixtral - cozygrid12 - 10-14-2026
Quote:Good point. The pattern around NVFP4 has been pretty similar for me. Worth rechecking your defaults though, because one bad assumption can make the re
Thanks, that helps. That matches what I saw on 4090. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: quiet dual-GPU build advice for Mixtral - macrolab - 10-14-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.
Re: quiet dual-GPU build advice for Mixtral - homelabhenry - 10-14-2026
I think the bottleneck is somewhere else. I get why that seems right, but on 5090 the bottleneck felt elsewhere. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: quiet dual-GPU build advice for Mixtral - tensorport - 10-16-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context.
Re: quiet dual-GPU build advice for Mixtral - sanevault - 10-16-2026
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: quiet dual-GPU build advice for Mixtral - bytegarden73 - 10-16-2026
Maybe, but I had the opposite result. I've seen people blame prefix caching 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 for Mixtral - amberpatch25 - 10-16-2026
same here on my side.