# Daniel Han says V3.1 quants beat GSQ and V3 on efficiency

> Original title: Yes our main goal was to make quants better on the Pareto efficiency front! So vs GSQ & V3 quants, V3.1 is much better!

- Source: Daniel Han
- Published: 2026-11-06T00:16:27.000Z
- Bad Influence: https://badinfluence.news/items/xbqrqt2wky8ejqdlo1k4g1wjq
- Original: https://x.com/danielhanchen/status/2118497703797854584

## Summary

Daniel 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.

## Post

Yes our main goal was to make quants better on the Pareto efficiency front! So vs GSQ & V3 quants, V3.1 is much better!

Avg recovery of UD-IQ3_XXS is 99.9% & UD-IQ2_XS at 99.4% whilst being smaller than IQ3_S - the diffs are largest on small bits - UD-IQ1_S 97.9% vs GSQ 90.5%

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWZpOhSaoAAeDkK.jpg&mode=thumb&exp=1794182400&sig=072db5e6cce9d683)

## Quoted post @orenoa7

> UD-IQ3_XXSを動かしてみたけど、結局サイズが既存IQ3_Sと変わらず速度向上はdecodeで+0.7〜2.3%程度
> 
> ただしベンチマークスコアはUD-IQ3_XXS側がTerminalBench2.1はじめ9/12の指標で上回っている
> 
> UD系列で面白いのはUD-IQ2_XSだと考えていて、サイズは75.8GBでIQ3_Sより7.8GB減量している
> 
> こちらはBF16比精度がIQ3_Sに対し+0.4pt改善していて、各種ベンチマークスコアも既存IQ3_Sに近い
> 
> IQ3_Sがサイズの問題で使えなかった人はUD-IQ2_XSに乗り換える意義が大きと思う

https://x.com/orenoa7/status/2118217731468341286