The paper systematically studies decode‑phase energy consumption of open‑source large language models using different attention architectures—Multi‑Head Attention (MHA), Grouped Query Attention (GQA), and GQA with Sliding Window Attention (SWA). It evaluates four models across varying context lengths, batch sizes, and generation workloads, measuring GPU energy via NVIDIA counters. Findings show that the attention mechanism is the main driver of how energy scales with context length, with MHA models growing steeply, GQA models growing less, and GQA+SWA remaining nearly constant; model size mainly sets absolute energy use, while batching can cut energy per token and latency by up to 87%.
By Molka Chkir, Syed Muhammad Danish, Jos H\"oll, Arghavan Asad
The paper introduces agentic-eCAL, an extension of the Energy Cost of AI Lifecycle metric to evaluate multi‑agent AI workflows across the edge‑cloud continuum. By combining a two‑rate energy model with OSI‑layer transport analysis, the authors quantify that inter‑agent text transfer accounts for only 0.25% of total workflow energy, highlighting that the main energy cost lies in additional inference and context processing triggered by communication. The study uses extensive GPU benchmarks on NVIDIA A100/H100 with 16 open‑weight models and 8 orchestration topologies to validate the metric and explore placement implications.
By Carolina Fortuna, Vid Han\v{z}el, Tim Strnad, Bla\v{z} Bertalani\v{c}
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:2609.33965v2 Announce Type: replace-cross
Abstract: We describe a methodology for estimating the per-token energy cost of cloud-hosted large language model (LLM) inference, separating between i...
By Joshua Horswill, Ross Hunter, Matt Clifford, James Hall
The paper investigates the energy costs of multilingual large language model (LLM) inference, revealing significant disparities across languages. Using the ML.Energy framework, the authors find that energy consumption per output token can differ by up to 8.3×, and total energy for a fixed request set can vary up to 179×, with English being the cheapest and Pashto the most expensive. The study attributes these differences to higher per-token costs for complex or rare scripts and longer outputs for low‑resource languages, and notes that high‑energy languages also tend to have lower task accuracy.
By Naihao Deng, Alissa Shen, Yiming Feng, Joan Nwatu, Jae-Won Chung, Mosharaf Chowdhury, Yulong Chen, Rada Mihalcea
The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems. However, direct measurement of inference energy often requires hardware telemetry, power instrumentation, or infrastructure-specific monitoring, limiting its applicability in comparative studies, early-stage system design, and sustainability reporting.
arXiv:2608. 00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots.
By Banruo Liu, Haoran Qiu, \'I\~nigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Esha Choukse
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:2609.35760v2 Announce Type: replace-cross
Abstract: When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The age...
By Chaoqian Ouyang, Ling Yue, Libin Zheng, Hanghui Guo, Shengxiang Xu, YiShu Wang, Ran Li, Jian Yin, Shaowu Pan, Shimin Di
arXiv:2610.28576v1 Announce Type: new
Abstract: Energy-efficient deployment of large language models requires understanding how model architecture, hardware, and serving settings shape energy per gen...
By Chenxu Niu, Batuhan Sencer, Wei Zhang, Yong Chen
arXiv:2607. 26571v1 Announce Type: new Abstract: The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprint of deployed AI systems.
By Tina Vartziotis, Rodopi Kosteli, Elli Vartziotis, George Dasoulas, Michael Keckeisen, Konstantinos Skianis, Sotirios Kotsopoulos, Francesca Dominici
The paper presents a systematic study of token consumption in AI agents performing coding tasks. It finds that agentic tasks are far more expensive—about 1000 times more tokens than code reasoning or chat—primarily due to input tokens, and that token usage varies wildly, with accuracy peaking at moderate costs. Models differ significantly in efficiency, and current frontier models cannot reliably predict their own token usage, often underestimating it.
By Longju Bai, Zhemin Huang, Xingyao Wang, Jiao Sun, Rada Mihalcea, Erik Brynjolfsson, Alex Pentland, Jiaxin Pei