Metrics and evaluations for computational and sustainable AI efficiency
By: Hongyuan Liu, Xinyang Liu, Guosheng Hu
Potential Business Impact:
Measures AI's speed, energy, and pollution.
The rapid advancement of Artificial Intelligence (AI) has created unprecedented demands for computational power, yet methods for evaluating the performance, efficiency, and environmental impact of deployed models remain fragmented. Current approaches often fail to provide a holistic view, making it difficult to compare and optimise systems across heterogeneous hardware, software stacks, and numeric precisions. To address this gap, we propose a unified and reproducible methodology for AI model inference that integrates computational and environmental metrics under realistic serving conditions. Our framework provides a pragmatic, carbon-aware evaluation by systematically measuring latency and throughput distributions, energy consumption, and location-adjusted carbon emissions, all while maintaining matched accuracy constraints for valid comparisons. We apply this methodology to multi-precision models across diverse hardware platforms, from data-centre accelerators like the GH200 to consumer-level GPUs such as the RTX 4090, running on mainstream software stacks including PyTorch, TensorRT, and ONNX Runtime. By systematically categorising these factors, our work establishes a rigorous benchmarking framework that produces decision-ready Pareto frontiers, clarifying the trade-offs between accuracy, latency, energy, and carbon. The accompanying open-source code enables independent verification and facilitates adoption, empowering researchers and practitioners to make evidence-based decisions for sustainable AI deployment.
Similar Papers
Toward Sustainable Generative AI: A Scoping Review of Carbon Footprint and Environmental Impacts Across Training and Inference Stages
Computers and Society
Helps AI use less energy and be greener.
AI Work Quantization Model: Closed-System AI Computational Effort Metric
Performance
Measures AI work like human work for fair pay.
Measuring the environmental impact of delivering AI at Google Scale
Artificial Intelligence
Measures AI's energy use, showing it's less than thought.