iPhone 18 Pro runs 27B models 2x faster; tease of 100B+ local LLM on iPhone

MannyKayy · x · 2026-09-21

Developer @adrgrondin reports the iPhone 18 Pro's A20 Pro chip exceeds expectations for on-device AI, running a 27B parameter model at twice the speed of the iPhone 17 Pro. @MannyKayy reposts teasing a demo of a 100B+ parameter model running locally on an iPhone with minimal performance loss and double-digit tokens/s — "watch this space." If real, on-device AI hardware is closing in on cloud-grade model capability fast.

Original post →

More from Infra

Infra channel →