Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

Abstract

Large language models (LLMs) offer powerful capabilities but come with significant environmental impact, particularly in carbon emissions. Existing studies benchmark carbon emissions but lack a standardized basis for comparison across different model configurations. To address this, we introduce the concept of functional unit (FU) as a standardized basis and develop FUEL, the first FU-based framework for evaluating LLM serving's environmental impact. Through three case studies, we uncover key insights and trade-offs in reducing carbon emissions by optimizing model size, quantization strategy, and hardware choice, paving the way for more sustainable LLM serving. The code is available at https://github.com/jojacola/FUEL.

17 pages, 38 figures, Proceedings of the The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, July 27-August 1st, 2025