Aaron Tilley / The Information:

PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech  —  Apple is on a quest to shrink powerful AI models to run on iPhones, which could cut down on cloud computing costs and enhance user privacy.

Aaron Tilley / The Information:

PrismML shrunk Qwen 3.6 to 27B parameters and ran it on an iPhone 17 Pro, bigger than any prior mobile model; sources: Apple talked with PrismML about its tech  —  Apple is on a quest to shrink powerful AI models to run on iPhones, which could cut down on cloud computing costs and enhance user privacy.

Source: TechMeme
Source Link: https://www.techmeme.com/260709/p14#a260709p14