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.
By \'Edouard Gu\'egain, Tristan Coignion
arXiv:2606. 27841v1 Announce Type: cross Abstract: The widespread adoption of Artificial Intelligence (AI) has led to increasing concerns about energy consumption, yet there is a lack of standardized methodologies to accurately estimate AI inference energy consumption, particularly across various tasks and architectures.
By Adrien Sardi, Marie-Line Alberi Morel, Sara Alouf, Fr\'ed\'eric Giroire, Joanna Moulierac
arXiv:2607. 09400v1 Announce Type: cross Abstract: Adaptive power management in Electric Vehicles (EVs) requires accurate power prediction.
By Avik Bhatnagar, Anton Paule, Tobias Schuermann, Sebastian Reiter, Oliver Bringmann
arXiv:2608. 03589v1 Announce Type: new Abstract: We present a method for designing deep neural networks (DNNs) for intermittent, energy-autonomous, on-device learning on microcontroller units (MCUs).
By Jakob Schubert, Maximilian Kasper, Maximilian Linke, Benedict Herzog, Mark Deutel, Axel Plinge, Dominik Seuss, Christopher Mutschler
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
The paper examines how deployment constraints such as strict latency deadlines and cumulative energy budgets can overturn traditional accuracy-based model selection for time‑series tasks. Using handover prediction in cellular networks as a case study, the authors evaluate eight architectures, screening for deadline feasibility at the tail and then ranking the feasible models by measured inference energy, including feature‑computation costs. Gradient‑boosted trees on handcrafted temporal features achieve the highest accuracy (F1 = 0.974) and are also among the cheapest to run, whereas a neural architecture that would rank first by accuracy alone (CNN‑1D, F1 = 0.914) consumes over three times more energy per inference under realistic duty‑cycled deployment.
whyItMatters":"The study demonstrates that accuracy‑only benchmarking can mislead deployment decisions by favoring models that are infeasible under real‑world latency and energy constraints."
By Shruti Bothe, Illyyne Saffar, Ayush K. Varshney