+- 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: 7900 XTX local stack: worth it? (/showthread.php?tid=502)
7900 XTX local stack: worth it? - phasetrack - 09-26-2026
Posting this in case it saves someone else a little time.
I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about small local stacks.
Simple and boring is a valid answer.
Re: 7900 XTX local stack: worth it? - papermixer4 - 09-27-2026
Quote:Posting this in case it saves someone else a little time.
Good point. I ended up in about the same place using Ollama.
Re: 7900 XTX local stack: worth it? - dockworks23 - 09-27-2026
I tested this tonight. On Threadripper box with PyTorch, I saw basically the same behavior. The main thing that moved was latency, not quality.
Re: 7900 XTX local stack: worth it? - relaynest82 - 09-28-2026
Quote:I tested this tonight. On Threadripper box with PyTorch, I saw basically the same behavior. The main thing that moved was latency, not quality.
Good point. 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.
Re: 7900 XTX local stack: worth it? - rocmpath - 09-29-2026
Appreciate the detail. That matches what I saw on Threadripper box. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: 7900 XTX local stack: worth it? - papermixer4 - 09-29-2026
My first guess would be this: If you're on PyTorch, I'd confirm the version first and then reduce variables until the behavior is obvious.