mlsanityData to 7 Oct 2026

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

arXiv 2502.11256 ↗First posted 16 Feb 2025cs.LG cs.AR cs.CLcited by 11

Not on the map. Why?

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 30 of its 57 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

30 of 57 references.

References · 30

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2024Qwen2.5 Technical Reportcited by 4,713
  8. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  9. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  10. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  11. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  12. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
18 more
  1. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  2. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  3. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
  4. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  5. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 536
  6. 2024Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Servecited by 507
  7. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  8. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 480
  9. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  10. 2024Skywork-Reward: Bag of Tricks for Reward Modeling in LLMscited by 322
  11. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  12. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  13. 2023TIGERScore: Towards Building Explainable Metric for All Text Generation Taskscited by 69
  14. 2024Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Servicescited by 44
  15. 2024LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferencescited by 19
  16. 2023Toward Sustainable HPC: Carbon Footprint Estimation and Environmental Implications of HPC Systemscited by 12
  17. 2024Towards Sustainable Large Language Model Servingcited by 12
  18. 2024GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissionscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Energy Considerations of Large Language Model Inference and Efficiency Optimizationscited by 54
  2. 2025The Energy Cost of Reasoning: Analyzing Energy Usage in LLMs with Test-time Computecited by 14
  3. 2025Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspectivecited by 8
  4. 2025EnsembleCI: Ensemble Learning for Carbon Intensity Forecastingcited by 5
  5. 2026Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorialcited by 4
  6. 2026Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameterscited by 1
  7. 2026BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Servingcited by 1
  8. 2025The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluationscited by 0
  9. 2026Evaluation of ML Resource Utilization Requires Model Life Cycle Assessmentcited by 0
  10. 2026From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sectorcited by 0
  11. 2026Beyond Energy: When Sustainability Dimensions Reshape LLM Serving Decisionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Large Language Models (LLMs): Deployment, Tokenomics and Sustainability
  2. 2026Wasted large language models: A life cycle thinking approach
  3. 2025What can large language models do for sustainable food?
  4. 2023LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models
  5. 2026The Energy Footprint of LLM-Based Environmental Analysis: LLMs and Domain Products
  6. 2025Cache Your Prompt When It's Green: Carbon-Aware Caching for Large Language Model Serving
  7. 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges
  8. 2026Environmental Footprint of GenAI Research: Insights from the Moshi Foundation Model