+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Evaluation & Testing (https://www.datasculpting.ai/inference/forumdisplay.php?fid=16)
+--- Forum: Benchmarks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=65)
+--- Thread: comparing models without fooling yourself: early impressions (/showthread.php?tid=25)
comparing models without fooling yourself: early impressions - benchplease - 08-24-2026
Did a bit of testing and thought I'd post the result here.
I tried this with Mistral using MLX on mini PC. The headline result was better than I expected, but token cost still ended up being the limiting factor.
Nothing scientific here, just practical notes from a real setup.
Re: comparing models without fooling yourself: early impressions - cacheline - 08-24-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.