# MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

> Source: <https://aiflash.com/news/149719/>
> Published: 2026-11-11 12:00:05+00:00

Weight-activation quantization can reduce the memory and compute cost of neural-network inference, but recent methods often require expensive optimization and architecture-specific propagation of basis transforms across layers. We introduce MACaQ, an MXFP4 W4A4 post-training quantization method that