# Benchmarking Energy Efficiency of Large Language Models Using vLLM

arXiv: https://arxiv.org/abs/2509.08867 · HTML: https://mlsanity.com/paper/2509.08867/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 8 of 8)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [Measuring the Carbon Intensity of AI in Cloud Instances](https://mlsanity.com/paper/2206.05229/) (2022)
- [Energy Usage Reports: Environmental awareness as part of algorithmic accountability](https://mlsanity.com/paper/1911.08354/) (2019)
- [Exploring the Carbon Footprint of Hugging Face's ML Models: A Repository Mining Study](https://mlsanity.com/paper/2305.11164/) (2023)

## Built on by (most cited first, 3 of 3)

- [Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations](https://mlsanity.com/paper/2607.09172/) (2026)
- [Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption](https://mlsanity.com/paper/2607.04553/) (2026)
- [The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models](https://mlsanity.com/paper/2609.31341/) (2026)

## Abstract (arXiv)

The prevalence of Large Language Models (LLMs) is having an growing impact on the climate due to the substantial energy required for their deployment and use. To create awareness for developers who are implementing LLMs in their products, there is a strong need to collect more information about the energy efficiency of LLMs. While existing research has evaluated the energy efficiency of various models, these benchmarks often fall short of representing realistic production scenarios. In this paper, we introduce the LLM Efficiency Benchmark, designed to simulate real-world usage conditions. Our benchmark utilizes vLLM, a high-throughput, production-ready LLM serving backend that optimizes model performance and efficiency. We examine how factors such as model size, architecture, and concurrent request volume affect inference energy efficiency. Our findings demonstrate that it is possible to create energy efficiency benchmarks that better reflect practical deployment conditions, providing valuable insights for developers aiming to build more sustainable AI systems.