+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Miscellaneous Discussion (https://www.datasculpting.ai/inference/forumdisplay.php?fid=24)
+--- Forum: Off Topic (https://www.datasculpting.ai/inference/forumdisplay.php?fid=27)
+--- Thread: what music do you benchmark to (/showthread.php?tid=563)
what music do you benchmark to - bytehall - 09-29-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Mixtral, llama.cpp, dual 3090, with a lot of attention on continuous batching.
Feel free to tear it apart if you see something dumb.
This is mostly for local work rather than public serving.
Re: what music do you benchmark to - phasestream53 - 09-29-2026
I hit almost the same issue last night.
Re: what music do you benchmark to - batchpeak - 09-29-2026
That matches what I was seeing. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.