AFM 3 Core Advanced: how Apple fit 20 billion parameters into iPhone

Apple's AFM 3 Core Advanced is a 20-billion-parameter multimodal model that runs entirely on-device on iPhone, activating only 1–4 billion neurons per query via sparse architecture and NAND flash storage.

Author: Michael Kokin ·

At WWDC 2026, Apple unveiled AFM 3 Core Advanced — the flagship third-generation multimodal model. The neural network runs entirely on-device on iPhone and iPad, with no personal data sent to external servers. Here's how they pulled it off.

How it works

Where it's used

The model is deeply integrated into iOS 27 and other new Apple operating systems — powering an upgraded Siri, image generation, and advanced voice recognition. MacStories are calling it a historic breakthrough: Apple's engineers implemented Instruction-Following Pruning, an algorithm that elegantly routes around the mobile memory bottleneck.

Limitations

The architecture is tightly optimized, but only hits its full potential on the latest Apple Silicon chips. Older devices will still be offloading heavy tasks to the cloud.