AI Report: Minor Tweaks Slash Energy Use by 90%

New research published by UNESCO and UCL, shows that small changes to how Large Language Models are built and used can dramatically reduce energy consumption without compromising performance. The report advocates for a pivot away from resource-heavy AI models in favour of more compact models. Used together, these measures can reduce energy consumption by up to 90%.

Generative AI's annual energy footprint is already equivalent to that of a low-income country, and it is growing exponentially. To make AI more sustainable, we need a paradigm shift in how we use it, and we must educate consumers about what they can do to reduce their environmental impact.

Tawfik JelassiAssistant Director-General for Communication and Information, UNESCO

Ensuring better use and development of artificial intelligence

UNESCO has a mandate to support its 194 Member States in their digital transformations, providing them with insights to develop energy-efficient, ethical and sustainable AI policies. In 2021 the Organization's Member States unanimously adopted the UNESCO Recommendation on the Ethics of AI, a governance framework which includes a policy-oriented chapter on AI's impact on the environment and ecosystems.

This new report calls on governments and industry to invest in sustainable AI research and development, as well as AI literacy, to empower users to better understand the environmental impact of their AI use and make more informed decisions.

Accessible and effective solutions to reduce the environmental impact of AI

Generative AI tools are now used by over 1 billion people daily. Each interaction consumes energy-about 0.34 watt-hours per prompt. This adds up to 310 gigawatt-hours per year, equivalent to the annual electricity use of over 3 million people in a low-income African country.

For this report, a team of computer scientists at UCL carried out a series of original experiments on a range of different open-source Large Language Models (LLMs). They identified three innovations which enable substantial energy savings, without compromising the accuracy of the results:

  1. Smaller models are just as smart and accurate as large ones: Small models tailored to specific tasks can cut energy use by up to 90%. Currently, users rely on large, general-purpose models for all their needs. The research shows that using smaller models tailored to specific tasks-like translation or summarization-can cut energy use significantly without losing performance. It's a smarter, more cost and resource efficient approach: matching the right model to the right job, instead of turning to one large, all-purpose system for everything.

Developers also have a role to play in the design process: the so-called 'mixture of experts' model is an on-demand system incorporating many smaller, specialized models. Each model - for example, a summarizing model or a translation model - is only activated when needed to accomplish a specific task.

  1. Shorter, more concise prompts and responses can reduce energy use by over 50%.

  1. Model-compression can save up to 44% in energy. Reducing the size of models through techniques such as quantization helps them use less energy while maintaining accuracy.

Small models are more accessible

Most AI infrastructure is currently concentrated in high-income countries, leaving others behind and deepening global inequalities. According to the ITU, only 5% of Africa's AI talent has access to the computing power needed to build or use generative AI. The three techniques explored in the report are particularly useful in low-resource settings, where energy and water are scarce; small models are much more accessible in low-resource environments with limited connectivity.

About UNESCO

With 194 Member States, the United Nations Educational, Scientific and Cultural Organization contributes to peace and security by leading multilateral cooperation on education, science, culture, communication and information. Headquartered in Paris, UNESCO has offices in 54 countries and employs over 2300 people. UNESCO oversees more than 2000 World Heritage sites, Biosphere Reserves and Global Geoparks; networks of Creative, Learning, Inclusive and Sustainable Cities; and over 13 000 associated schools, university chairs, training and research institutions, with a global network of 200 National Commissions. Its Director-General is Audrey Azoulay.

"Since wars begin in the minds of men, it is in the minds of men that the defenses of peace must be constructed" - UNESCO Constitution, 1945.

/Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.