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.
More from Infra
- Laya, an open-source local AI, is being built into Omarchy M to run on Apple GPUs and ANE — Scobleizer · 2026-09-21
- Facebook and Instagram down for thousands of users in ongoing outage — Polymarket · 2026-09-21
- Agent builders say provider KV caching black boxes block swarm and long-run agents — Small_Luck8177 · 2026-09-21
- Laya ported to MLX: M3 Max runs local agent 60 decisions/sec, 50x faster — sven_ai · 2026-09-21
- US Data Center and Info-Processing Hardware Spending Now Exceeds Housing Investment — rohanpaul_ai · 2026-09-21
- Intel's BITCOS compresses ternary LLMs to 1.485 bits per weight, boosting decode up to 27% — burny_tech · 2026-09-21