+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: AMD / ROCm (https://www.datasculpting.ai/inference/forumdisplay.php?fid=32)
+--- Thread: Instinct pricing thoughts (/showthread.php?tid=1081)
Pages:
1
2
Re: Instinct pricing thoughts - rocmriley - 10-17-2026
That matches what I was seeing. The pattern around tokens/sec has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer. The logs were somehow calmer than I was.
Re: Instinct pricing thoughts - quantshed - 10-17-2026
I'd approach it in a boring order. If you're on Ollama, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: Instinct pricing thoughts - papermixer4 - 10-17-2026
Not sure I agree there. I get why that seems right, but on M3 Max the bottleneck felt elsewhere.
Re: Instinct pricing thoughts - audiopath66 - 10-17-2026
What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
Re: Instinct pricing thoughts - routecraft - 10-17-2026
Quote:What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?
A couple questions before I guess too hard. Are you testing this on A6000 or something else?