+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Evals (https://www.datasculpting.ai/inference/forumdisplay.php?fid=66)
+--- Thread: human evals on small teams for Gemma (/showthread.php?tid=226)
Pages:
1
2
Re: human evals on small teams for Gemma - relaynest82 - 09-16-2026
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.
Re: human evals on small teams for Gemma - lablab - 09-16-2026
What exact setup are you running? Is this local-only or are you routing anything externally?
Re: human evals on small teams for Gemma - macroforge - 09-16-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Gemma and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.