mlsanityData to 14 Oct 2026

Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights

arXiv 2504.06307 ↗First posted 7 Apr 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

The rapid adoption of large language models (LLMs) has led to significant energy consumption and carbon emissions, posing a critical challenge to the sustainability of generative AI technologies. This paper explores the integration of energy-efficient optimization techniques in the deployment of LLMs to address these environmental concerns. We present a case study and framework that demonstrate how strategic quantization and local inference techniques can substantially lower the carbon footprints of LLMs without compromising their operational effectiveness. Experimental results reveal that these methods can reduce energy consumption and carbon emissions by up to 45% post quantization, making them particularly suitable for resource-constrained environments. The findings provide actionable insights for achieving sustainability in AI while maintaining high levels of accuracy and responsiveness.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 15 of its 28 references that are in the map. First posted on arXiv 7 Apr 2025.

Builds on

15 of 28 references.

References · 15

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  3. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  5. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  6. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
  7. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
  8. 2022Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Modelcited by 265
  9. 2023A Systematic Review of Green AIcited by 77
  10. 2020FrugalML: How to Use ML Prediction APIs More Accurately and Cheaplycited by 33
  11. 2024Towards Optimizing the Costs of LLM Usagecited by 33
  12. 2023Greening Large Language Models of Codecited by 19
3 more
  1. 2024Efficient and Green Large Language Models for Software Engineering: Literature Review, Vision, and the Road Aheadcited by 17
  2. 2024Green AI: Exploring Carbon Footprints, Mitigation Strategies, and Trade Offs in Large Language Model Trainingcited by 15
  3. 2023Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagationcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramidcited by 0
  2. 2025EnviroLLM: Resource Tracking and Optimization for Local AIcited by 0
  3. 2026The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Addressing the sustainable AI trilemma: a case study on LLM agents and RAG
  2. 2025Systematic Weight Evaluation for Pruning Large Language Models: Enhancing Performance and Sustainability
  3. 2025Benchmarking Energy Efficiency of Large Language Models Using vLLM
  4. 2026Sustainable LLM Inference using Context-Aware Model Switching
  5. 2026Balancing Sustainability And Performance: The Role Of Small-Scale LLMs In Agentic Artificial Intelligence Systems
  6. 2025Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques
  7. 2025Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models
  8. 2025GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation