Intelligence Per Watt: A Study of Local Intelligence Efficiency

Jon Saad-Falcon; Avanika Narayan; Hakki Orhun Akengin; J. Wes Griffin; Herumb Shandilya; Adrian Gamarra Lafuente; Medhya Goel; Rebecca Joseph; Shlok Natarajan; Etash Kumar Guha; Shang Zhu; Ben Athiwaratkun; John Hennessy; Azalia Mirhoseini; Christopher Ré

doi:10.48550/arXiv.2511.07885

Intelligence Per Watt: A Study of Local Intelligence Efficiency

Jon Saad-Falcon* Stanford

Avanika Narayan* Stanford University

Hakki Orhun Akengin Stanford University

J. Wes Griffin Stanford University

Herumb Shandilya Stanford University

Adrian Gamarra Lafuente Stanford

Medhya Goel Stanford University

Rebecca Joseph Stanford University

Shlok Natarajan Stanford

Etash Kumar Guha Stanford University

Shang Zhu Together AI

Ben Athiwaratkun Together AI

John Hennessy Stanford University

Azalia Mirhoseini Stanford University

Christopher Ré Stanford University

Preprint, 2025

DOI: 10.48550/arXiv.2511.07885

We introduce intelligence-per-watt (IPW) to measure how efficiently inference systems convert energy into useful computation. Local LMs accurately respond to 88.7% of single-turn chat and reasoning queries, with local intelligence efficiency improving 5.3x from 2023-2025.

Materials

Bibtex

@misc{2025ipw,
  title = {Intelligence Per Watt: A Study of Local Intelligence Efficiency},
  author = {Jon Saad-Falcon and Avanika Narayan and Hakki Orhun Akengin and J. Wes Griffin and Herumb Shandilya and Adrian Gamarra Lafuente and Medhya Goel and Rebecca Joseph and Shlok Natarajan and Etash Kumar Guha and Shang Zhu and Ben Athiwaratkun and John Hennessy and Azalia Mirhoseini and Christopher Ré},
  booktitle = {Preprint},
  year = {2025},
  doi = {10.48550/arXiv.2511.07885},
  url = {https://arxiv.org/abs/2511.07885},
}

Scaling Intelligence Lab

Intelligence Per Watt: A Study of Local Intelligence Efficiency

Materials

Bibtex