Energy efficiency in LLM inference has improved 100,000x in the past 10 years — demonstrating that accelerated computing is sustainable computing. Josh Parker, head of sustainability at NVIDIA, explains how. #ClimateWeekNYC

Learn more: https://t.co/vcmmpQALjx pic.twitter.com/I0s7tNceCd

— NVIDIA (@nvidia) 25 septembre 2025

Energy efficiency in LLM inference has improved 100,000x in the past 10 years — demonstrating that accelerated computing is sustainable computing. Josh Parker, head of sustainability at NVIDIA, explains how. #ClimateWeekNYC Learn more: https://
nvda.ws/4nIymWu

→ View original post on X — @nvidia