+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: throughput per watt reality check for Mistral (/showthread.php?tid=1051)
Pages:
1
2
Re: throughput per watt reality check for Mistral - tinycontext - 10-15-2026
Quote:That matches what I was seeing. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make t
That matches what I was seeing. I ended up in about the same place using TensorRT-LLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: throughput per watt reality check for Mistral - flintriver50 - 10-18-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there.
Re: throughput per watt reality check for Mistral - cacheworks - 10-18-2026
Did a small comparison this afternoon. My result was mixed: first run looked bad, second run looked normal. The surprise was that memory pressure showed up before throughput collapsed.
Re: throughput per watt reality check for Mistral - kernelhouse70 - 10-19-2026
I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.