# Preprint reports more accurate four-bit inference using shift-and-add arithmetic

_Published Friday, October 16, 2026 at 2:06 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report a four-bit language-model quantization method that replaces multiplication with integer shifts and additions while retaining performance close to a conventional integer baseline. Their preprint introduces a finer weight grid to address accuracy losses in existing power-of-two quantization.

On Llama-3-8B with four-bit weights and activations, the method improved zero-shot commonsense reasoning performance by 8.72% relative to the power-of-two baseline, while trailing the uniform integer baseline by 0.4 percentage points. Calibration absorbs approximation errors into the weights and scaling. The proposed processing element uses fewer gates than a four-bit integer multiplier; the reported results span seven models and three bit-widths.

## Sources

- [cs.LG updates on arXiv.org](https://arxiv.org/abs/2610.21257)

---
Canonical: https://techandbusiness.org/newswire/UG7rjjGeBDnEglFf0Eli9g
Published: 2026-10-16T06:06:14.306Z
Story chronology: 2026-10-16T04:00:00.000Z
Retrieved: 2026-10-16T08:36:28.569Z
Publisher: Tech & Business (techandbusiness.org)