Score: 1

CO2-Meter: A Comprehensive Carbon Footprint Estimator for LLMs on Edge Devices

Published: November 11, 2025 | arXiv ID: 2511.08575v1

By: Zhenxiao Fu, Chen Fan, Lei Jiang

Potential Business Impact:

Measures computer brain's energy use for greener AI.

Business Areas:
Smart Cities Real Estate

LLMs have transformed NLP, yet deploying them on edge devices poses great carbon challenges. Prior estimators remain incomplete, neglecting peripheral energy use, distinct prefill/decode behaviors, and SoC design complexity. This paper presents CO2-Meter, a unified framework for estimating operational and embodied carbon in LLM edge inference. Contributions include: (1) equation-based peripheral energy models and datasets; (2) a GNN-based predictor with phase-specific LLM energy data; (3) a unit-level embodied carbon model for SoC bottleneck analysis; and (4) validation showing superior accuracy over prior methods. Case studies show CO2-Meter's effectiveness in identifying carbon hotspots and guiding sustainable LLM design on edge platforms. Source code: https://github.com/fuzhenxiao/CO2-Meter

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
9 pages

Category
Computer Science:
Hardware Architecture