← Back to People
Author of "Intelligence Per Watt: Measuring Intelligence Efficiency of Local AI" on arXiv
1
Mentions
1
Articles
1
Outlets
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Herumb Shandilya
Article Types
- research1
Media Angles
- technical1
Narrative Framing
- breakthrough1
Writes About
Articles
Most recent firstArticles Written
Herumb Shandilya as author
Intelligence Per Watt: Measuring Intelligence Efficiency of Local AI
arXivresearchpositiveNov 18, 2025
Local inference using small language models (≤20B parameters) can accurately answer 88.7% of real-world queries while achieving 5.3x improvement in intelligence-per-watt efficiency from 2023-2025, enabling meaningful redistribution of demand from centralized cloud infrastructure.
“Author of "Intelligence Per Watt: Measuring Intelligence Efficiency of Local AI" on arXiv”
LLMsAI InfrastructureAI Chips/HardwareAI Research