BigGrizzly

la source :
How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference
▻https://arxiv.org/pdf/2505.09598

This paper introduces an infrastructure-aware benchmarking framework for quanti- fying the environmental footprint of LLM inference across 30 state-of-the-art mod- els in commercial datacenters. The framework combines public API performance data with company-specific environmental multipliers and statistical inference of hardware configurations. We additionally utilize cross-efficiency Data Envelopment Analysis (DEA) to rank models by performance relative to environmental cost and provide a dynamically updated dashboard that visualizes model-level energy, water, and carbon metrics. Results show the most energy-intensive models exceed 29 Wh per long prompt, over 65× the most efficient systems. Even a 0.42 Wh short query, when scaled to 700M queries/day, aggregates to annual electricity comparable to 35,000 U.S. homes, evaporative freshwater equal to the annual drink- ing needs of 1.2M people, and carbon emissions requiring a Chicago-sized forest to offset. These findings highlight a growing paradox: as AI becomes cheaper and faster, global adoption drives disproportionate resource consumption. Our methodology offers a standardized, empirically grounded basis for sustainability benchmarking and accountability in AI deployment.

et le résumé graphique par Reporter

https://images.jifo.co/142224516_1780395435232.jpg

Pas terrible l’infographie, j’ai imaginé le contraire avant de réfléchir un peu plus !

#effet_rebond bien entendu, #IA #IAgen #électricité #eau #énergie #pollution #CO2 #réchauffement_climatique