# Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection

arXiv: https://arxiv.org/abs/2510.01889 · HTML: https://mlsanity.com/paper/2510.01889/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 73 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 30 of 31)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink](https://mlsanity.com/paper/2204.05149/) (2022)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Measuring the Carbon Intensity of AI in Cloud Instances](https://mlsanity.com/paper/2206.05229/) (2022)
- [ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network](https://mlsanity.com/paper/1811.11431/) (2018)
- [Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training](https://mlsanity.com/paper/2208.06102/) (2022)
- [NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes](https://mlsanity.com/paper/2312.14890/) (2023)
- [ImagenHub: Standardizing the evaluation of conditional image generation models](https://mlsanity.com/paper/2310.01596/) (2023)
- [Hype, Sustainability, and the Price of the Bigger-is-Better Paradigm in AI](https://mlsanity.com/paper/2409.14160/) (2024)
- [Artificial Intelligence Index Report 2024](https://mlsanity.com/paper/2405.19522/) (2024)
- [A survey on Variational Autoencoders from a GreenAI perspective](https://mlsanity.com/paper/2103.01071/) (2021)
- [ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition](https://mlsanity.com/paper/2210.13352/) (2022)
- [Benchmarking Representations for Speech, Music, and Acoustic Events](https://mlsanity.com/paper/2405.00934/) (2024)
- [Energy Consumption of Deep Generative Audio Models](https://mlsanity.com/paper/2107.02621/) (2021)
- [The Power of Training: How Different Neural Network Setups Influence the Energy Demand](https://mlsanity.com/paper/2401.01851/) (2024)

## Built on by (most cited first, 3 of 3)

- [A collaborative agent with two lightweight synergistic models for autonomous crystal materials research](https://mlsanity.com/paper/2604.11540/) (2026)
- [Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction](https://mlsanity.com/paper/2606.22606/) (2026)
- [Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs](https://mlsanity.com/paper/2608.11830/) (2026)

## Abstract (arXiv)

The energy consumption and carbon footprint of Artificial Intelligence (AI) have become critical concerns due to rising costs and environmental impacts. In response, a new trend in green AI is emerging, shifting from the "bigger is better" paradigm, which prioritizes large models, to "small is sufficient", emphasizing energy sobriety through smaller, more efficient models. We explore how the AI community can adopt energy sobriety today by focusing on model selection during inference. Model selection consists of choosing the most appropriate model for a given task, a simple and readily applicable method, unlike approaches requiring new hardware or architectures. Our hypothesis is that, as in many industrial activities, marginal utility gains decrease with increasing model size. Thus, applying model selection can significantly reduce energy consumption while maintaining good utility for AI inference. We conduct a systematic study of AI tasks, analyzing their popularity, model size, and efficiency. We examine how the maturity of different tasks and model adoption patterns impact the achievable energy savings, ranging from 1% to 98% for different tasks. Our estimates indicate that applying model selection could reduce AI energy consumption by 27.8%, saving 31.9 TWh worldwide in 2025 - equivalent to the annual output of five nuclear power reactors.