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

arXiv: https://arxiv.org/abs/2502.11256 · HTML: https://mlsanity.com/paper/2502.11256/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [RewardBench: Evaluating Reward Models for Language Modeling](https://mlsanity.com/paper/2403.13787/) (2024)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs](https://mlsanity.com/paper/2410.18451/) (2024)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks](https://mlsanity.com/paper/2310.00752/) (2023)
- [Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services](https://mlsanity.com/paper/2404.16283/) (2024)
- [LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences](https://mlsanity.com/paper/2410.02950/) (2024)
- [Toward Sustainable HPC: Carbon Footprint Estimation and Environmental Implications of HPC Systems](https://mlsanity.com/paper/2306.13177/) (2023)
- [Towards Sustainable Large Language Model Serving](https://mlsanity.com/paper/2501.01990/) (2024)
- [GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions](https://mlsanity.com/paper/2412.20322/) (2024)

## Built on by (most cited first, 11 of 11)

- [Energy Considerations of Large Language Model Inference and Efficiency Optimizations](https://mlsanity.com/paper/2504.17674/) (2025)
- [The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Compute](https://mlsanity.com/paper/2505.14733/) (2025)
- [Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective](https://mlsanity.com/paper/2508.16712/) (2025)
- [EnsembleCI: Ensemble Learning for Carbon Intensity Forecasting](https://mlsanity.com/paper/2505.01959/) (2025)
- [Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial](https://mlsanity.com/paper/2602.19534/) (2026)
- [Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters](https://mlsanity.com/paper/2602.17697/) (2026)
- [BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving](https://mlsanity.com/paper/2605.27480/) (2026)
- [The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations](https://mlsanity.com/paper/2507.13302/) (2025)
- [Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment](https://mlsanity.com/paper/2606.07632/) (2026)
- [From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector](https://mlsanity.com/paper/2608.17827/) (2026)
- [Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisions](https://mlsanity.com/paper/2609.35569/) (2026)

## Abstract (arXiv)

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.