It’s no secret that AI comes with an environmental cost. According to the International Energy Agency, data centers consumed around 415 terawatt-hours of electricity in 2025 — roughly 1.5% of global electricity demand — and that figure is projected to climb to about 945 TWh by 2030, largely driven by AI growth. In the U.S., the agency says data centers accounted for around half of all electricity demand growth in 2025. That doesn’t mean AI is inherently bad for the planet, but it does mean every prompt has a footprint — which is exactly why smaller, more efficient AI models deserve more attention this Earth Day...and every day.
When most people think about AI, they picture the biggest names like ChatGPT, Gemini or Claude. Unfortunately, those big names come with big electricity and water useage, too. While AI can help solve real-world problems, it’s fair to ask whether every task needs a system designed to solve quantum physics just to rewrite an email.
That's where small language models, often called SLMs can be useful. And yes, they are exactly what they sound like, AI models built to be smaller and more efficient than the most popular chatbots. And after spending time with them, I’m starting to think they’re a smarter fit for everyday life.
