paper-with-me

Papers

SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment

2025-11-17 · Jiacheng Wang, Yejun Zeng, Jinyang Guo, Yuqing Ma, Aishan Liu, Xianglong Liu arxiv

Despite the growing interest in Small Language Models (SLMs) as resource-efficient alternatives to Large Language Models (LLMs), their deployment on edge devices remains challenging due to unresolved efficiency gaps in model compression. While quantization has proven effective for LLMs, its applicability to SLMs is significantly underexplored, with critical questions about differing quantization bottlenecks and efficiency profiles. This paper introduces SLMQuant, the first systematic benchmark for evaluating LLM compression techniques when applied to SLMs. Through comprehensive multi-track evaluations across diverse architectures and tasks, we analyze how state-of-the-art quantization methods perform on SLMs. Our findings reveal fundamental disparities between SLMs and LLMs in quantization sensitivity, demonstrating that direct transfer of LLM-optimized techniques leads to suboptimal results due to SLMs' unique architectural characteristics and training dynamics. We identify key factors governing effective SLM quantization and propose actionable design principles for SLM-tailored compression. SLMQuant establishes a foundational framework for advancing efficient SLM deployment on low-end devices in edge applications, and provides critical insights for deploying lightweight language models in resource-constrained scenarios.

📄 PDF Abstract BibTeX arXiv:2511.13023

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

2024-05-09 · Ruihao Gong, Yang Yong, Shiqiao Gu, Yushi Huang 외

Recent advancements in large language models (LLMs) are propelling us toward artificial general intelligence with their remarkable emergent abilities and reasoning capabilities. However, the substantial computational and…

BenchmarkingComputational EfficiencyLanguage ModelingLanguage Modelling+2

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats

2026-01-14 · Manyi Zhang, Ji-Fu Li, Zhongao Sun, Haoli Bai 외 arxiv

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms being proposed, they mostly focus on intege…

A Survey of Small Language Models

2024-10-25 · Chien Van Nguyen, Xuan Shen, Ryan Aponte, Yu Xia 외

Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, making them ideal for various settings inclu…

BenchmarkingModel CompressionQuantizationSurvey

OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models

2023-06-04 · Changhun Lee, Jungyu Jin, Taesu Kim, HyungJun Kim 외

Large language models (LLMs) with hundreds of billions of parameters require powerful server-grade GPUs for inference, limiting their practical deployment. To address this challenge, we introduce the outlier-aware weight…

parameter-efficient fine-tuningQuantization

Automatic Mixed-Precision Quantization Search of BERT

2021-12-30 · Changsheng Zhao, Ting Hua, Yilin Shen, Qian Lou 외

Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks. However, these models usually contain millions of parameters, which prevents them from practical …

Knowledge DistillationModel CompressionNeural Architecture SearchQuantization