arXiv Machine Learning By \'Edouard Gu\'egain, Tristan Coignion

The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices

Read the original on arXiv Machine Learning →

The paper investigates the environmental impact of running large language models (LLMs) on mobile devices. It evaluates 18 different LLM configurations on two smartphones and a server, measuring energy per token, latency, accuracy, and battery-cycle consumption. Findings reveal that on-device inference is about three times less energy‑efficient than batched server inference, that energy consumption varies non‑monotonically with quantization bit‑width, and that most models are not on the Pareto front of accuracy and energy efficiency. The study concludes that local AI is not inherently more sustainable than cloud inference, with the majority of environmental impact stemming from device embodied carbon.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computation and Language
Sep 3

How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?

The paper investigates how prompt design influences energy consumption in on-device large language models (LLMs). It examines two prompt properties—cognitive load and phrasing pattern—across various datasets, models, and devices, using phase-level profiling to separate prefill and decode energy. Findings show that cognitive load mainly affects energy per token, while phrasing pattern influences energy mainly through token usage, and that prompt design reshapes the energy-quality trade‑off differently for each model.

By Wei Hu, Xiaolong Tu, Dawei Chen, Yitao Chen, Kyungtae Han, Haoxin Wang
arXiv Machine Learning
Jun 24

EnerInfer: Energy-Aware On-Device LLM Inference

arXiv:2606. 23001v1 Announce Type: cross Abstract: On-device LLM inference is increasingly attractive for privacy-preserving, reliable, and cost-effective deployment, yet its energy and thermal costs remain a critical bottleneck.

By Bohua Zou, Nian Liu, Binqi Sun, Matteo Mascherin, Debayan Roy, Yutao Liu, Yu Peng, Ning Jia, Haibo Chen