The same AI question emits more carbon dioxide in Texas than in Sweden

Swedish AI company Berget AI, with researchers from the Stockholm Environment Institute, WattTime and Klimatkollen, released an open-source method for calculating the carbon dioxide emissions of individual AI requests, publishing the code on GitHub and a web-based calculator at co2.berget.ai. Under the method, a typical request to the Kimi K3 model emits about 0.4 grams of CO2 in Sweden, 1.6 grams in Ireland, 2.5 grams in Germany and 3.2 grams in Texas on identical hardware. Berget AI says the aim is to make the AI industry's climate impact more transparent and let companies compare suppliers.

The Swedish AI company Berget AI, together with researchers from the Stockholm Environment Institute SEI and the organizations WattTime and Klimatkollen, has developed a new method https://berget.ai/en/blog/per-request-co2-press-release for calculating how much carbon dioxide different AI requests generate. The aim is to make the AI industry’s climate impact more transparent and give companies the opportunity to compare different suppliers. According to the method, for example, a typical request to the AI model Kimi K3 results in around 0.4 grams of carbon dioxide emissions in Sweden, 1.6 grams in Ireland, 2.5 grams in Germany, and 3.2 grams in Texas. Despite identical hardware. Berget AI has published the method as open source https://github.com/berget-ai/co2-calculator , meaning other companies can freely use it. A web-based calculator https://co2.berget.ai/ also makes it possible to compare emissions between different AI models and geographical regions.