# Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations

arXiv: https://arxiv.org/abs/2503.23934 · HTML: https://mlsanity.com/paper/2503.23934/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 53 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 22 of 22)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink](https://mlsanity.com/paper/2204.05149/) (2022)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning](https://mlsanity.com/paper/1611.05128/) (2016)
- [The rising costs of training frontier AI models](https://mlsanity.com/paper/2405.21015/) (2024)
- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutions](https://mlsanity.com/paper/2305.18339/) (2023)
- [Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmission](https://mlsanity.com/paper/2404.09134/) (2024)
- [Combining Generative and Discriminative Models for Hybrid Inference](https://mlsanity.com/paper/1906.02547/) (2019)
- [The Price of Prompting: Profiling Energy Use in Large Language Models Inference](https://mlsanity.com/paper/2407.16893/) (2024)
- [A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges](https://mlsanity.com/paper/2412.04782/) (2024)
- [Computing Within Limits: An Empirical Study of Energy Consumption in ML Training and Inference](https://mlsanity.com/paper/2406.14328/) (2024)
- [Large Generative AI Models meet Open Networks for 6G: Integration, Platform, and Monetization](https://mlsanity.com/paper/2410.18790/) (2024)
- [An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2](https://mlsanity.com/paper/2411.12758/) (2024)
- [Energy-Rate-Quality Tradeoffs of State-of-the-Art Video Codecs](https://mlsanity.com/paper/2210.00618/) (2022)
- [FROST: Towards Energy-efficient AI-on-5G Platforms -- A GPU Power Capping Evaluation](https://mlsanity.com/paper/2310.11131/) (2023)
- [Adapting MLOps for Diverse In-Network Intelligence in 6G Era: Challenges and Solutions](https://mlsanity.com/paper/2410.18793/) (2024)
- [AI-Native Multi-Access Future Networks -- The REASON Architecture](https://mlsanity.com/paper/2411.06870/) (2024)

## Built on by (most cited first, 2 of 2)

- [Dissecting Transformers: A CLEAR Perspective towards Green AI](https://mlsanity.com/paper/2510.02810/) (2025)
- [The Hidden Environmental Cost of Poor Coding Practices in TensorFlow and Keras Applications: A Study on Resource Leaks and Carbon Emissions](https://mlsanity.com/paper/2606.19799/) (2026)

## Abstract (arXiv)

This study presents an empirical investigation into the energy consumption of Discriminative and Generative AI models within real-world MLOps pipelines. For Discriminative models, we examine various architectures and hyperparameters during training and inference and identify energy-efficient practices. For Generative AI, Large Language Models (LLMs) are assessed, focusing primarily on energy consumption across different model sizes and varying service requests. Our study employs software-based power measurements, ensuring ease of replication across diverse configurations, models, and datasets. We analyse multiple models and hardware setups to uncover correlations among various metrics, identifying key contributors to energy consumption. The results indicate that for Discriminative models, optimising architectures, hyperparameters, and hardware can significantly reduce energy consumption without sacrificing performance. For LLMs, energy efficiency depends on balancing model size, reasoning complexity, and request-handling capacity, as larger models do not necessarily consume more energy when utilisation remains low. This analysis provides practical guidelines for designing green and sustainable ML operations, emphasising energy consumption and carbon footprint reductions while maintaining performance. This paper can serve as a benchmark for accurately estimating total energy use across different types of AI models.