A Caltech spinout called PrismML released a compressed 27-billion-parameter AI model on July 14 that fits in under 4 GB of memory and runs on any iPhone 15 or newer, and Apple is actively testing whether the underlying technology could change how the company handles on-device AI. PrismML CEO Babak Hassibi confirmed to CNBC that Apple and unnamed other companies have been evaluating the startup's models, measuring speed, energy efficiency, and device-level performance. "They're really evaluating our technology right now," Hassibi said of Apple, characterizing the discussions as early-stage but adding that "things are progressing nicely." Apple opened the first public beta of iOS 27 on July 13. PrismML's Bonsai 27B reduces each weight to a single bit in its binary variant or to one of three values in its ternary variant, using a technique called FP16 group-wise scaling. The result is a 1-bit binary model at 3.9 GB that retains more than 90% of the base model's performance across 15 combined evaluations, and a 1.58-bit ternary model at 5.9 GB that retains more than 95%. On an iPhone 17 Pro, the 1-bit model runs at 11 tokens per second.