Metraipolis › archive › dc_9b5da110da88
The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices — arXiv:2609.11940
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11940
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:08:45.383Z
- SHA-256 of the archived text
2dd4b9b1fd5247be4a54a588841c1f328a5e23def5efac88179d6259f638add5- Stable URL of this page
https://metraipolis.com/documento/dc_9b5da110da88
How to cite
The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices — arXiv:2609.11940 — arXiv (en), https://arxiv.org/abs/2609.11940 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b5da110da88 (Metraipolis archive dc_9b5da110da88, sha256 2dd4b9b1fd5247be4a54a588841c1f328a5e23def5efac88179d6259f638add5)
BibTeX
@misc{dc9b5da110da88,
title = {The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices — arXiv:2609.11940},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11940},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b5da110da88; sha256 2dd4b9b1fd5247be4a54a588841c1f328a5e23def5efac88179d6259f638add5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11940. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.PF). Categorie arXiv: Performance (cs.PF) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.11940 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T03:03:37.609Z dalla pagina https://arxiv.org/catchup/cs.PF/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).