Saved in:
Bibliographic Details
Main Authors: Putzky, Patrick, Genzel, Martin, Mollenhauer, Mattes, Schulze, Sebastian, Wollmann, Thomas, Dietzel, Stefan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.22787
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910271094652928
author Putzky, Patrick
Genzel, Martin
Mollenhauer, Mattes
Schulze, Sebastian
Wollmann, Thomas
Dietzel, Stefan
author_facet Putzky, Patrick
Genzel, Martin
Mollenhauer, Mattes
Schulze, Sebastian
Wollmann, Thomas
Dietzel, Stefan
contents Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibility but suffer from functional collapse at extreme bit-rates below 4 bits. On the other hand, techniques leveraging calibration data or extensive recovery training achieve superior fidelity but impose high computational constraints and face uncertain robustness under data distribution shifts. We introduce EntQuant, a framework that unites the advantages of these distinct paradigms. By matching the performance of data-dependent methods with the speed and universality of data-free techniques, EntQuant enables practical utility in the extreme compression regime. Our method decouples numerical precision from storage cost via entropy coding, compressing a 70B parameter model in less than 10 minutes. We demonstrate that EntQuant does not only achieve state-of-the-art results on standard evaluation sets and models, but also retains functional performance on more complex benchmarks with instruction-tuned models, all at modest inference overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22787
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Float8@2bits: Entropy Coding Enables Data-Free Model Compression
Putzky, Patrick
Genzel, Martin
Mollenhauer, Mattes
Schulze, Sebastian
Wollmann, Thomas
Dietzel, Stefan
Machine Learning
Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibility but suffer from functional collapse at extreme bit-rates below 4 bits. On the other hand, techniques leveraging calibration data or extensive recovery training achieve superior fidelity but impose high computational constraints and face uncertain robustness under data distribution shifts. We introduce EntQuant, a framework that unites the advantages of these distinct paradigms. By matching the performance of data-dependent methods with the speed and universality of data-free techniques, EntQuant enables practical utility in the extreme compression regime. Our method decouples numerical precision from storage cost via entropy coding, compressing a 70B parameter model in less than 10 minutes. We demonstrate that EntQuant does not only achieve state-of-the-art results on standard evaluation sets and models, but also retains functional performance on more complex benchmarks with instruction-tuned models, all at modest inference overhead.
title Float8@2bits: Entropy Coding Enables Data-Free Model Compression
topic Machine Learning
url https://arxiv.org/abs/2601.22787