AI RESEARCH
Intelligence per Watt: Measuring Intelligence Efficiency of Local AI
arXiv CS.CL
•
ArXi:2511.07885v4 Announce Type: replace-cross Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can scale. Two advances create an opportunity to rethink it: small, local LMs (<=20B active parameters) now achieve competitive performance to frontier models on many tasks, and local accelerators (e.g., Apple M4 Max) can host these models at interactive latencies.