Balancing Sustainability And Performance: The Role Of Small-Scale LLMs In Agentic Artificial Intelligence Systems

TL;DR

This paper explores how small-scale language models can be used in agentic AI systems to reduce energy consumption while maintaining performance, providing practical guidelines for sustainable AI development.

Contribution

It demonstrates that smaller open-weight models can lower energy use without sacrificing task quality and offers strategies for sustainable AI system design.

Findings

Smaller models reduce energy consumption significantly.

Performance remains stable with smaller models in tested environments.

Provides guidelines for resource allocation and batch sizing for sustainability.

Abstract

As large language models become integral to agentic artificial intelligence systems, their energy demands during inference may pose significant sustainability challenges. This study investigates whether deploying smaller-scale language models can reduce energy consumption without compromising responsiveness and output quality in a multi-agent, real-world environments. We conduct a comparative analysis across language models of varying scales to quantify trade-offs between efficiency and performance. Results show that smaller open-weights models can lower energy usage while preserving task quality. Building on these findings, we propose practical guidelines for sustainable artificial intelligence design, including optimal batch size configuration and computation resource allocation. These insights offer actionable strategies for developing scalable, environmentally responsible artificial intelligence systems.