An Empirical Study of Qwen3 Quantization

• URL: http://arxiv.org/abs/2505.02214v1
• Date: Sun, 04 May 2025 18:43:44 GMT
• Title: An Empirical Study of Qwen3 Quantization
• Authors: Xingyu Zheng, Yuye Li, Haoran Chu, Yue Feng, Xudong Ma, Jie Luo, Jinyang Guo, Haotong Qin, Michele Magno, Xianglong Liu,
• Abstract summary: Low-bit quantization presents a promising solution, yet its impact on Qwen3's performance remains underexplored.<n>We rigorously assess 5 existing classic post-training quantization techniques applied to Qwen3, spanning bit-widths from 1 to 8 bits.<n>Our findings reveal that while Qwen3 maintains competitive performance at moderate bit-widths, it experiences notable degradation in linguistic tasks under ultra-low precision.
• Score: 30.214896404069677
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Qwen series has emerged as a leading family of open-source Large Language Models (LLMs), demonstrating remarkable capabilities in natural language understanding tasks. With the recent release of Qwen3, which exhibits superior performance across diverse benchmarks, there is growing interest in deploying these models efficiently in resource-constrained environments. Low-bit quantization presents a promising solution, yet its impact on Qwen3's performance remains underexplored. This study conducts a systematic evaluation of Qwen3's robustness under various quantization settings, aiming to uncover both opportunities and challenges in compressing this state-of-the-art model. We rigorously assess 5 existing classic post-training quantization techniques applied to Qwen3, spanning bit-widths from 1 to 8 bits, and evaluate their effectiveness across multiple datasets. Our findings reveal that while Qwen3 maintains competitive performance at moderate bit-widths, it experiences notable degradation in linguistic tasks under ultra-low precision, underscoring the persistent hurdles in LLM compression. These results emphasize the need for further research to mitigate performance loss in extreme quantization scenarios. We anticipate that this empirical analysis will provide actionable insights for advancing quantization methods tailored to Qwen3 and future LLMs, ultimately enhancing their practicality without compromising accuracy. Our project is released on https://github.com/Efficient-ML/Qwen3-Quantization and https://huggingface.co/collections/Efficient-ML/qwen3-quantization-68164450decb1c868788cb2b.

Related papers

• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models [90.54780244175511]
  We introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series.<n>The Qwen3 Embedding series offers a spectrum of model sizes for both embedding and reranking tasks.<n>The Qwen3 Embedding series achieves state-of-the-art results across diverse benchmarks.
  arXiv  Detail & Related papers  (2025-06-05T15:49:48Z)
• InfiJanice: Joint Analysis and In-situ Correction Engine for Quantization-Induced Math Degradation in Large Language Models [39.257022875813284]
  Large Language Models (LLMs) have demonstrated impressive performance on complex reasoning benchmarks such as GSM8K, MATH, and AIME.<n>Model quantization has emerged as a promising approach to reduce memory footprint and inference latency.<n>We show that quantization can degrade mathematical reasoning accuracy by up to 69.81%.
  arXiv  Detail & Related papers  (2025-05-16T12:11:40Z)
• Qwen3 Technical Report [137.96804244102205]
  We present Qwen3, the latest version of the Qwen model family.<n>Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, and multilingual capabilities.
  arXiv  Detail & Related papers  (2025-05-14T13:41:34Z)
• An Efficient Quantum Classifier Based on Hamiltonian Representations [50.467930253994155]
  Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks.<n>We propose an efficient approach that circumvents the costs associated with data encoding by mapping inputs to a finite set of Pauli strings.<n>We evaluate our approach on text and image classification tasks, against well-established classical and quantum models.
  arXiv  Detail & Related papers  (2025-04-13T11:49:53Z)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph [83.90988015005934]
  Uncertainty quantification is a key element of machine learning applications.<n>We introduce a novel benchmark that implements a collection of state-of-the-art UQ baselines.<n>We conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.
  arXiv  Detail & Related papers  (2024-06-21T20:06:31Z)
• SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks [1.0923877073891446]
  Spiking neural networks (SNNs) share the goal of enhancing efficiency, but adopt an 'event-driven' approach to reduce the power consumption of neural network inference. This paper introduces two QAT schemes for stateful neurons: (i) a uniform quantization strategy, an established method for weight quantization, and (ii) threshold-centered quantization. Our results show that increasing the density of quantization levels around the firing threshold improves accuracy across several benchmark datasets.
  arXiv  Detail & Related papers  (2024-04-15T03:07:16Z)
• Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study [90.34226812493083]
  This work aims to investigate the impact of quantization on emphemergent abilities, which are important characteristics that distinguish LLMs from small language models. Our empirical experiments show that these emergent abilities still exist in 4-bit quantization models, while 2-bit models encounter severe performance degradation. To improve the performance of low-bit models, we conduct two special experiments: (1) fine-gained impact analysis that studies which components (or substructures) are more sensitive to quantization, and (2) performance compensation through model fine-tuning.
  arXiv  Detail & Related papers  (2023-07-16T15:11:01Z)
• Designing strong baselines for ternary neural network quantization through support and mass equalization [7.971065005161565]
  Deep neural networks (DNNs) offer the highest performance in a wide range of applications in computer vision. This computational burden can be dramatically reduced by quantizing floating point values to ternary values. We show experimentally that our approach allows to significantly improve the performance of ternary quantization through a variety of scenarios.
  arXiv  Detail & Related papers  (2023-06-30T07:35:07Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.