Skip to content
Trending storyDeveloping

Daniel Han reports V3.1 UD quants beat GSQ and V3 on efficiency

1 article1 sourcesince Nov 5Last article 2h ago ·

Overview

AISummary of 1 article

Daniel Han says the UD quants for DeepSeek V3.1 beat GSQ and V3 quants on the Pareto efficiency front, per a post on X. He reports that UD-IQ3_XXS recovers 99.9% of average accuracy and UD-IQ2_XS recovers 99.4%, and both are smaller than IQ3_S. The largest gap appears at the smallest quant: UD-IQ1_S recovers 97.9% of accuracy versus 90.5% for GSQ.

Written by AI from the articles below · updated Nov 5, 7:58 PM ET

Check the sources:

Latest developmentNov 5, 7:16 PM ET
Daniel Han says V3.1 quants beat GSQ and V3 on efficiency

Article timeline

The articles in this story. Times are ET.

Nov 5
  1. Daniel HanX
    Daniel Han says V3.1 quants beat GSQ and V3 on efficiency

    AIDaniel Han says the UD quants for V3.1 beat GSQ and V3 quants on the Pareto efficiency front. UD-IQ3_XXS recovers 99.9% of average accuracy and UD-IQ2_XS recovers 99.4%, both smaller than IQ3_S. The largest gap is on the smallest quant, where UD-IQ1_S recovers 97.9% versus 90.5% for GSQ.

    Image from @danielhanchen's post

Heat Trend

Not enough continuous observations to show a trend yet.