Gemma 4 E4B IQ2_XXS: + 140.54% Reasoning Performance From Tensor Level Quantization Allocation
英文标题：Gemma 4 E4B IQ2_XXS: + 140.54% Reasoning Performance From Tensor Level Quantization Allocation
iq2_xxs tensor level allocation recovered reasoning from 28.9 -> 69.5 at the same 3.3gb budget. https://huggingface.co/ByteOtter/gemma-4-E4B-it-CADA-IQ2_XXS I posted my Gemma 4 12B q3 result a couple days ago, where tensor level allocation gave me an +8.55% relative improvement over the categ
打开原文相关 2 · 机会 0
中文
iq2_xxs tensor level allocation recovered reasoning from 28.9 -> 69.5 at the same 3.3gb budget. https://huggingface.co/ByteOtter/gemma-4-E4B-it-CADA-IQ2_XXS I posted my Gemma 4 12B q3 result a couple days ago, where tensor level allocation gave me an +8.55% relative improvement over the categ
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
iq2_xxs tensor level allocation recovered reasoning from 28.9 -> 69.5 at the same 3.3gb budget. https://huggingface.co/ByteOtter/gemma-4-E4B-it-CADA-IQ2_XXS I posted my Gemma 4 12B q3 result a couple days ago, where tensor level allocation gave me an +8.55% relative improvement over the categ