---
title: "New paper: From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs"
description: "TWT Science & Innovation publishes \"From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs\" in arXiv preprint arXiv:2607.26571 (2026); accepted for oral presentation at GREEN-AI: Grounding Research on Energy- and resource-Efficient Networks for sustainable AI…"
url: https://greencode.ai/news/paper-from-tokens-to-watt-hours-analytical-energy-estimation-for-l/
---

# New paper: From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs

- 01 July, 2026
- GreenCode

### New paper: From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs

Large language model inference is a growing part of the environmental footprint of AI systems, yet measuring its energy directly usually needs hardware telemetry, power instruments or infrastructure-specific monitoring. That rules direct measurement out for many comparative studies, early design decisions and sustainability reports. This report sets out a way to estimate inference energy on NVIDIA H100-class GPUs without measuring at run time. The estimator combines transformer arithmetic counts scaled by model size, calibrated memory-traffic factors and hardware-specific energy figures for tensor-core computation and high-bandwidth memory access. It treats prompt processing separately from token-by-token generation, so it can estimate energy for input tokens, output tokens and whole requests. It also splits total energy into computation, parameter access, key-value cache writes and attention reads, showing how energy scales with model size, context length and the number of tokens generated. The estimates are not meant to replace physical power measurement; they are transparent, reproducible approximations with explicit assumptions, suited to comparing models, green coding analysis and design-time evaluation of inference workloads.

**Authors:** [Tina Vartziotis](https://greencode.ai/researchers/tina-vartziotis/), [Rodopi Kosteli](https://greencode.ai/researchers/rodopi-kosteli/), [Elli Danae Vartziotis](https://greencode.ai/researchers/elli-danae-vartziotis/), [George Dasoulas](https://greencode.ai/researchers/george-dasoulas/), [Michael Keckeisen](https://greencode.ai/researchers/michael-keckeisen/), [Konstantinos Skianis](https://greencode.ai/researchers/konstantinos-skianis/), [Sotirios Kotsopoulos](https://greencode.ai/researchers/sotirios-kotsopoulos/), [Francesca Dominici](https://greencode.ai/researchers/francesca-dominici/)

**Contributing partner:** [TWT Science & Innovation](https://greencode.ai/partners/twt-gmbh-science-innovation/)

[Publication page and citation](https://greencode.ai/publications/from-tokens-to-watt-hours-analytical-energy-estimation-for-llm-inference-on-mode/) [View at the publisher](https://doi.org/10.48550/arXiv.2607.26571)

#### Categories

- All news **(43)**
- Publications **(25)**
- Project news **(14)**
- Articles **(4)**

#### Recent Post

- #### [greenai.guide: plain-English help for using AI with less energy](https://greencode.ai/news/greenai-guide/)

  [Read more](https://greencode.ai/news/greenai-guide/)
- #### [New paper: IP-Preserving Enterprise System Modernization via LLM-Driven Specification Extraction and Multi-target Code Generation](https://greencode.ai/news/paper-ip-preserving-enterprise-system-modernization-via-llm-driven/)

  [Read more](https://greencode.ai/news/paper-ip-preserving-enterprise-system-modernization-via-llm-driven/)
- #### [New paper: (How) Do Large Language Models Understand High-Level Message Sequence Charts?](https://greencode.ai/news/paper-how-do-large-language-models-understand-high-level-message-s/)

  [Read more](https://greencode.ai/news/paper-how-do-large-language-models-understand-high-level-message-s/)
- #### [GreenCode is now on YouTube and TikTok](https://greencode.ai/news/greencode-on-youtube-and-tiktok/)

  [Read more](https://greencode.ai/news/greencode-on-youtube-and-tiktok/)
