# PQuantML: A Tool for End-to-End Hardware-aware Model Compression

Source: [PQuantML: A Tool for End-to-End Hardware-aware Model Compression](<https://www.sota2.com/research/paper/69ca03a90636e5bf4afc94b9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-31T05:00:13.307Z

Authors: Roope Niemi, Anastasiia Petrovych, Arghya Ranjan Das, Enrico Lupi, Chang Sun, Dimitrios Danopoulos, Marlon Joshua Helbing, Mia Liu, Sebastian Dittmeier, Michael Kagan, Vladimir Loncar, Maurizio Pierini

Published: 2026-03-27T16:54:46.000Z

## Abstract

PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to environments with strict latency constraints, PQuantML simplifies training of compressed models by providing a unified interface to apply pruning and quantization, either jointly or individually. The library implements multiple pruning methods with different granularities, as well as fixed-point quantization with support for High-Granularity Quantization. We evaluate PQuantML on representative tasks such as the jet substructure classification, so-called jet tagging, an on-edge problem related to real-time LHC data processing. Using various pruning methods with fixed-point quantization, PQuantML achieves substantial parameter and bit-width reductions while maintaining accuracy. The resulting compression is further compared against existing tools, such as QKeras and HGQ.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Jet Substructure Classification on HLF JSC OpenML](<https://www.sota2.com/research/sota/jet-substructure-classification-on-hlf-jsc-openml.md>): Jet Substructure Classification; HLF JSC OpenML; Accuracy: 76.9.

- [Jet Substructure Classification on HLF JSC CERN Box](<https://www.sota2.com/research/sota/jet-substructure-classification-on-hlf-jsc-cern-box.md>): Jet Substructure Classification; HLF JSC CERN Box; Accuracy: 74.8.

- [Jet Substructure Classification on PLF JSC 128,3](<https://www.sota2.com/research/sota/jet-substructure-classification-on-plf-jsc-128-3.md>): Jet Substructure Classification; PLF JSC 128,3; Accuracy: 76.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.26595>)

[PDF](<https://arxiv.org/pdf/2603.26595.pdf>)