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.
More from Infra
- RL train-sample systems are frontier AI's hardest infra problem — and a trade secret — brianryhuang · 2026-10-16
- Local tuning of GLM-5.3-Flash on 2×GB10 lifts decode from 49 to 58 tok/s — EAccelerate_42 · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16
- Optuna creator Akiba: when 2 hyperparameters cost $20M, what's left for BO/HPO — Stefania_druga · 2026-10-16
- Amazon Proposes Per-Request Validated Evidence Caching for Production RAG — _reachsumit · 2026-10-16
- LinkedIn's TransX report: sequence transduction for recsys, +6.02% CTR in A/B tests — _reachsumit · 2026-10-16