Human brain runs on 20 watts; silicon equivalent needs 25 million times more energy

anselm · x · 2026-08-31

The human brain thinks on roughly 20 watts, while an artificial system doing equivalent work would need about 25 million times more energy—enough on paper to power a quarter of a million homes.

Researchers estimate a human-scale model of 20 billion neurons running on an exascale machine would draw around 0.5 GW, the demand of hundreds of thousands of households. That gap is a hard limit on copying the brain with conventional silicon, and a key reason labs are turning to neuromorphic chips.

Original post →

More from Infra

Infra channel →