+- 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: when video is still not worth the wait: anyone testing this? (/showthread.php?tid=519)
Pages:
1
2
when video is still not worth the wait: anyone testing this? - fastquill74 - 09-26-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Maybe useful as a starting point: Ollama on 4090, keeping tail latency in mind from the start.
Maybe useful as a starting point for newer folks.
I care more about stability than squeezing the last possible tokens/sec out of it.
I expected the biggest difference to come from the model, but the stack around it mattered at least as much.
Re: when video is still not worth the wait: anyone testing this? - plainworks - 09-28-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: when video is still not worth the wait: anyone testing this? - mintstream9 - 09-28-2026
Quote:Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Re: when video is still not worth the wait: anyone testing this? - vectorhouse71 - 09-28-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: when video is still not worth the wait: anyone testing this? - audionode8 - 09-28-2026
Good point. That matches what I saw on 5090.
Re: when video is still not worth the wait: anyone testing this? - batchyard - 09-28-2026
A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: when video is still not worth the wait: anyone testing this? - deltastation - 09-30-2026
A couple things I'd check first. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: when video is still not worth the wait: anyone testing this? - paperrunner - 09-30-2026
I'd approach it in a boring order. On A6000, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.
Re: when video is still not worth the wait: anyone testing this? - vectorpoint - 09-30-2026
Not sure I agree there. I get why that seems right, but on GB200 the bottleneck felt elsewhere.
Re: when video is still not worth the wait: anyone testing this? - circuitworks90 - 09-30-2026
I'd start with the simpler stack.