+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Optimization & Performance (https://www.datasculpting.ai/inference/forumdisplay.php?fid=10)
+--- Forum: Performance Tuning (https://www.datasculpting.ai/inference/forumdisplay.php?fid=42)
+--- Thread: consumer GPU serving economics on 4090 (/showthread.php?tid=46)
Pages:
1
2
Re: consumer GPU serving economics on 4090 - signalcraft14 - 09-04-2026
Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: consumer GPU serving economics on 4090 - localpatch - 09-06-2026
Quote:Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the
A couple questions before I guess too hard. Do you see the same thing with a smaller batch or shorter prompt?