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

arXiv: https://arxiv.org/abs/2609.11940 · HTML: https://mlsanity.com/paper/2609.11940/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [MELTing point: Mobile Evaluation of Language Transformers](https://mlsanity.com/paper/2403.12844/) (2024)
- [Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency](https://mlsanity.com/paper/2504.03360/) (2025)
- [From Efficiency Gains to Rebound Effects: The Problem of Jevons' Paradox in AI's Polarized Environmental Debate](https://mlsanity.com/paper/2501.16548/) (2025)
- [MobileQuant: Mobile-friendly Quantization for On-device Language Models](https://mlsanity.com/paper/2408.13933/) (2024)
- [Intelligence per Watt: Measuring Intelligence Efficiency of Local AI](https://mlsanity.com/paper/2511.07885/) (2025)
- [More than Carbon: Cradle-to-Grave environmental impacts of GenAI training on the Nvidia A100 GPU](https://mlsanity.com/paper/2509.00093/) (2025)
- [A Beginner's Guide to Power and Energy Measurement and Estimation for Computing and Machine Learning](https://mlsanity.com/paper/2412.17830/) (2024)
- [Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge](https://mlsanity.com/paper/2503.09114/) (2025)
- [Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights](https://mlsanity.com/paper/2504.06307/) (2025)
- [Choosing to Be Green: Advancing Green AI via Dynamic Model Selection](https://mlsanity.com/paper/2509.19996/) (2025)
- [The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound](https://mlsanity.com/paper/2510.09022/) (2025)
- [Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges](https://mlsanity.com/paper/2511.11624/) (2025)

## Abstract (arXiv)

The rapid diffusion of generative artificial intelligence raises privacy, latency, and performance concerns that motivate a shift toward "local-first" AI, where inferences are performed on the user's device instead of on remote cloud servers. This paradigm also places a significant computational load on battery-powered smartphones, potentially shortening battery life and increasing the overall replacement rate of mobile devices. This paper presents a systematic study of the energy consumption, performance, and accuracy of on-device large language model (LLM) inference. We evaluate 18 models from different model families, sizes, and quantization levels, on two modern smartphones and on a server, using the respective state-of-the-art for such deployments. We measure the energy per generated token, inter-token latency, model accuracy, and battery-cycle consumption. Our results show that (i) on-device inference is on average 3 times less energy-efficient than batched server inference; (ii) the relationship between quantization bit-width and energy per token is non-monotonic, with energy sweet spots on both tested smartphones; (iii) eight out of 18 model configurations lie on the Pareto front of accuracy and energy-efficiency, allowing practitioners to build battery-aware model routers; and (iv) realistic modeling assumptions do not allow local inference to be less environmentally impacting per token than batched server inference, with 88--90% of that impact attributable to device embodied carbon rather than electricity consumption. These findings challenge the premise that local AI is more sustainable than cloud inference, and motivate the need for context-aware and life-cycle-aware model selection when deploying edge AI on battery-powered mobile platforms.