+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Quality / Reliability Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=68)
+--- Thread: video model setup pain points (/showthread.php?tid=278)
Pages:
1
2
Re: video model setup pain points - thetanest - 09-19-2026
Interesting, I hadn't tried that. That matches what I saw on M3 Max.
Re: video model setup pain points - marbleyard32 - 09-20-2026
A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: video model setup pain points - kernelhouse70 - 09-21-2026
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Re: video model setup pain points - rocmriley - 09-21-2026
Quote:I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Could be a wo
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?