Adaptive Block-Scaled Data Types

ArXi:2603.28765v1 Announce Type: new NVFP4 has grown increasingly popular as a 4-bit format for quantizing large language models due to its hardware and its ability to retain useful information with relatively few bits per parameter. However, the format is not without limitations: recent work has shown that NVFP4 suffers from its error distribution, resulting in large amounts of quantization error on near-maximal values in each group of 16 values. In this work, we leverage this insight to design new Adaptive Block-Scaled Data Types that can adapt to the distribution of their input values.