Publication Type

Journal Article

Version

acceptedVersion

Publication Date

9-2025

Abstract

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to enable efficient LLM inference by reducing model size and computational overhead. In this study, we conduct a comprehensive analysis of 28 quantized LLMs from the Ollama library, which applies by default Post-Training Quantization (PTQ) and weight-only quantization techniques, deployed on an edge device (Raspberry Pi 4 with 4GB RAM). We evaluate energy efficiency, inference performance, and output accuracy across multiple quantization levels and task types. Models are benchmarked on five standardized datasets (CommonsenseQA, BIG-Bench Hard, TruthfulQA, GSM8K, and HumanEval), and we employ a high-resolution, hardware-based energy measurement tool to capture real-world power consumption. Our findings reveal the trade-offs between energy efficiency, inference speed, and accuracy in different quantization settings, highlighting configurations that optimize LLM deployment for resource-constrained environments. By integrating hardware-level energy profiling with LLM benchmarking, this study provides actionable insights for sustainable AI, bridging a critical gap in existing research on energy-aware LLM deployment.

Discipline

Software Engineering

Research Areas

Cybersecurity; Software and Cyber-Physical Systems

Areas of Excellence

Sustainability

Publication

ACM Transactions on Internet of Things

First Page

1

Last Page

34

ISSN

2691-1914

Identifier

10.1145/3767742

Publisher

Association for Computing Machinery (ACM)

Additional URL

https://doi.org/10.1145/3767742

Download

Share

COinS