Papers
arxiv:2508.03332

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models

Published on Aug 5
Authors:
,
,
,
,
,
,
,

Abstract

LieQ, a post-training quantization framework, achieves high accuracy in sub-7B models under extreme low-bit compression, outperforming existing methods and enabling deployment on edge devices.

AI-generated summary

Large language models with billions of parameters are often over-provisioned: many layers contribute little unique information yet dominate the memory and energy footprint during inference. We present LieQ, a metric-driven post-training quantization framework that addresses the critical challenge of maintaining accuracy in sub-7B models under extreme low-bit compression. Our method introduces three complementary layer-wise diagnostics-Perplexity Drop, Representational Compactness, and Top-k Energy Gain -that reveal a canonical division of labour across layers, enabling automatic bit-width allocation without gradient updates. Unlike existing approaches that suffer severe accuracy degradation at 2-3 bits precision, LieQ achieves state-of-the-art compression-accuracy trade-offs: on Qwen3-4B, it recovers 95.9% of FP16 baseline performance at 2.05-bit quantization, outperforming GPTQ by 19.7% and AWQ by 18.1% on average across seven zero-shot reasoning tasks. Applied to LLaMA3.2-3B, LieQ maintains 98.2% of baseline accuracy at 2.07-bit precision while enabling 4x memory reduction, establishing new paradigms for deploying small language models on resource-constrained edge devices.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.03332 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.03332 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.03332 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.