paper-with-me

홈 › Papers

Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges

2025-11-07 · Md Romyull Islam, Bobin Deng, Nobel Dhar, Tu N. Nguyen, Selena He, Yong Shi, Kun Suo arxiv

Cloud-based large language models (LLMs) and their variants have significantly influenced real-world applications. Deploying smaller models (i.e., small language models (SLMs)) on edge devices offers additional advantages, such as reduced latency and independence from network connectivity. However, edge devices' limited computing resources and constrained energy budgets challenge efficient deployment. This study evaluates the power efficiency of five representative SLMs - Llama 3.2, Phi-3 Mini, TinyLlama, and Gemma 2 on Raspberry Pi 5, Jetson Nano, and Jetson Orin Nano (CPU and GPU configurations). Results show that Jetson Orin Nano with GPU acceleration achieves the highest energy-to-performance ratio, significantly outperforming CPU-based setups. Llama 3.2 provides the best balance of accuracy and power efficiency, while TinyLlama is well-suited for low-power environments at the cost of reduced accuracy. In contrast, Phi-3 Mini consumes the most energy despite its high accuracy. In addition, GPU acceleration, memory bandwidth, and model architecture are key in optimizing inference energy efficiency. Our empirical analysis offers practical insights for AI, smart systems, and mobile ad-hoc platforms to leverage tradeoffs from accuracy, inference latency, and power efficiency in energy-constrained environments.

📄 PDF Abstract BibTeX arXiv:2511.11624

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Small Talk, Big Impact: The Energy Cost of Thanking AI

2026-01-29 · Julien Delavande, Regis Pierrard, Sasha Luccioni arxiv

Being polite is free - or is it? In this paper, we quantify the energy cost of seemingly innocuous messages such as ``thank you'' when interacting with large language models, often used by users to convey politeness. Usi…

Carbon Intensity-Aware Adaptive Inference of DNNs

2024-03-23 · Jiwan Jung

DNN inference, known for its significant energy consumption and the resulting high carbon footprint, can be made more sustainable by adapting model size and accuracy to the varying carbon intensity throughout the day. Ou…

Model Selection

The Ramifications of Making Deep Neural Networks Compact

2020-06-26 · Nandan Kumar Jha, Sparsh Mittal, Govardhan Mattela

The recent trend in deep neural networks (DNNs) research is to make the networks more compact. The motivation behind designing compact DNNs is to improve energy efficiency since by virtue of having lower memory footprint…

GPU

An Energy and Carbon Footprint Analysis of Distributed and Federated Learning

2022-06-21 · Stefano Savazzi, Vittorio Rampa, Sanaz Kianoush, Mehdi Bennis

Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers, raising environmental concerns due to computational and communication r…

Federated Learning

EcoLearn: Optimizing the Carbon Footprint of Federated Learning

2023-10-27 · Talha Mehboob, Noman Bashir, Jesus Omana Iglesias, Michael Zink 외

Federated Learning (FL) distributes machine learning (ML) training across edge devices to reduce data transfer overhead and protect data privacy. Since FL model training may span hundreds of devices and is thus resource-…

Federated Learning