+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Benchmarks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=65)
+--- Thread: benchmark result I don't trust: anyone testing this? (/showthread.php?tid=1295)
Pages:
1
2
benchmark result I don't trust: anyone testing this? - benchplease - 10-15-2026
Did a bit of testing and thought I'd post the result here.
After a few runs on dual 3090, I ended up with decent performance, but the setup only really made sense once I adjusted around router policy.
Nothing scientific here, just practical notes from a real setup.
Re: benchmark result I don't trust: anyone testing this? - northgrid33 - 10-16-2026
I tested this tonight. My result was mixed: first run looked bad, second run looked normal.
Re: benchmark result I don't trust: anyone testing this? - homelabhenry - 10-16-2026
My first guess would be this: If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: benchmark result I don't trust: anyone testing this? - cacheline - 10-17-2026
A couple questions before I guess too hard. Are you testing this on dual 3090 or something else?
Re: benchmark result I don't trust: anyone testing this? - northhall88 - 10-18-2026
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
Re: benchmark result I don't trust: anyone testing this? - quiethouse - 10-18-2026
Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
Maybe, but I had the opposite result. I've seen people blame VRAM headroom when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.
Re: benchmark result I don't trust: anyone testing this? - benchplease - 10-18-2026
Quote:Quote:I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
worth checking the driver first.
Re: benchmark result I don't trust: anyone testing this? - cacheline - 10-19-2026
What exact setup are you running? What model, what runtime, and roughly what context size?
Re: benchmark result I don't trust: anyone testing this? - northgrid33 - 10-19-2026
A couple things I'd check first. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: benchmark result I don't trust: anyone testing this? - nanobrook - 10-19-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. Not glamorous advice, but repeatable baselines save a lot of time.