# Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models

> Source: <https://aiflash.com/news/150224/>
> Published: 2026-11-12 09:00:03+00:00

Local language models can save memory by storing weights in fewer bits, and they can reduce sensitivity to the order of answer options by averaging a few reorderings. We ask whether the first makes the second worse, and which is the cheaper way to spend a fixed budget. On Qwen3-0.6B and Qwen3-1.7B w