PrismML says it ran a 27B-parameter Qwen 3.6 model on an iPhone 17 Pro, bigger than any prior on-device model; sources: Apple held talks with PrismML about it (Aaron Tilley/The Information)

<a href="https://www.theinformation.com/articles/khosla-backed-startup-claims-breakthrough-largest-ever-ai-model-iphone"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260709/i14.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260709/p14#a260709p14" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Aaron Tilley / <a href="https://www.theinformation.com/">The Information</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.theinformation.com/articles/khosla-backed-startup-claims-breakthrough-largest-ever-ai-model-iphone">PrismML says it ran a 27B-parameter Qwen 3.6 model on an iPhone 17 Pro, bigger than any prior on-device model; sources: Apple held talks with PrismML about it</a></b></span>&nbsp; &mdash;&nbsp; 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.</p>