+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: NVIDIA / CUDA (https://www.datasculpting.ai/inference/forumdisplay.php?fid=31)
+--- Thread: Blackwell deployment chatter for FLUX (/showthread.php?tid=622)
Pages:
1
2
Re: Blackwell deployment chatter for FLUX - kernelmike - 10-06-2026
Quote:worth checking the driver first.
That matches what I was seeing. I ended up in about the same place using llama.cpp. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Blackwell deployment chatter for FLUX - audiopath66 - 10-06-2026
A couple things I'd check first. On M3 Max, 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: Blackwell deployment chatter for FLUX - kernelmike - 10-09-2026
Thanks, that helps. That matches what I saw on A6000. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Blackwell deployment chatter for FLUX - latentgarden - 10-10-2026
Maybe, but I had the opposite result. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.