# Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations

arXiv: https://arxiv.org/abs/2507.11417 · HTML: https://mlsanity.com/paper/2507.11417/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2025.

## Built on by (most cited first, 12 of 12)

- [This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs](https://mlsanity.com/paper/2603.15699/) (2026)
- [Dissecting Transformers: A CLEAR Perspective towards Green AI](https://mlsanity.com/paper/2510.02810/) (2025)
- [KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving](https://mlsanity.com/paper/2604.16682/) (2026)
- [WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs](https://mlsanity.com/paper/2607.02391/) (2026)
- [Prefill vs. Decode Bottlenecks: SRAM-Frequency Tradeoffs and the Memory-Bandwidth Ceiling](https://mlsanity.com/paper/2512.22066/) (2025)
- [SEALing the Gap: A Reference Framework for LLM Inference Carbon Estimation via Multi-Benchmark Driven Embodiment](https://mlsanity.com/paper/2603.02949/) (2026)
- [LLMSpace: Carbon Footprint Modeling for Large Language Model Inference on LEO Satellites](https://mlsanity.com/paper/2605.05615/) (2026)
- [Tackling the Data-Parallel Load Balancing Bottleneck in LLM Serving: Practical Online Routing at Scale](https://mlsanity.com/paper/2605.06113/) (2026)
- [EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving](https://mlsanity.com/paper/2605.10556/) (2026)
- [Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs](https://mlsanity.com/paper/2608.11830/) (2026)
- [InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers](https://mlsanity.com/paper/2608.12915/) (2026)
- [Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling](https://mlsanity.com/paper/2609.19499/) (2026)

## Abstract (arXiv)

The environmental impact of Large Language Models (LLMs) is rising significantly, with inference now accounting for more than half of their total lifecycle carbon emissions. However, existing simulation frameworks, which are increasingly used to determine efficient LLM deployments, lack any concept of power and, therefore, cannot accurately estimate inference-related emissions. We present a simulation framework to assess the energy and carbon implications of LLM inference under varying deployment setups. First, we extend a high-fidelity LLM inference simulator with a GPU power model that estimates power consumption based on utilization metrics, enabling analysis across configurations like batch size, sequence length, and model parallelism. Second, we integrate simulation outputs into an energy system co-simulation environment to quantify carbon emissions under specific grid conditions and explore the potential of carbon-aware scheduling. Through scenario-based analysis, our framework reveals how inference parameters affect energy demand and carbon footprint, demonstrates a renewable offset potential of up to 69.2% in an illustrative deployment case, and provides a foundation for future carbon-aware inference infrastructure design.