Green LLM Techniques in Action: How Effective Are Existing Techniques for Improving the Energy Efficiency of LLM-Based Applications in Industry?
Abstract
The rapid adoption of large language models (LLMs) has raised concerns about their substantial energy consumption, especially when deployed at industry scale. While several techniques have been proposed to address this, limited empirical evidence exists regarding the effectiveness of applying them to LLM-based industry applications. To fill this gap, we analyzed a chatbot application in an industrial context at Schuberg Philis, a Dutch IT services company. We then selected four techniques, namely Small and Large Model Collaboration, Prompt Optimization, Quantization, and Batching, applied them to the application in eight variations, and then conducted experiments to study their impact on energy consumption, accuracy, and response time compared to the unoptimized baseline. Our results show that several techniques, such as Prompt Optimization and 2-bit Quantization, managed to reduce energy use significantly, sometimes by up to 90%. However, these techniques especially impacted accuracy negatively, to a degree that is not acceptable in practice.
2026 IEEE/ACM 48th International Conference on Software Engineering (ICSE-SEIP '26), Rio de Janeiro, Brazil, 12 pages
BibTeX
@inproceedings{Kuran2026,
author = {Kuran, Pelin Rabia and Chitakunye, Rumbidzai and Stoico, Vincenzo and Heitlager, Ilja and Bogner, Justus},
title = {Green LLM Techniques in Action: How Effective Are Existing Techniques for Improving the Energy Efficiency of LLM-Based Applications in Industry?},
booktitle = {2026 IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP '26)},
pages = {554--565},
year = {2026},
publisher = {ACM},
doi = {10.1145/3786583.3786896}
}