Apple is in talks with an AI startup, aiming to have its large language model run directly on the iPhone

robot
Abstract generation in progress
Golden Finance reports, July 15, citing CNBC: Apple is in preliminary talks with AI startup PrismML and is evaluating its AI model compression technology, with the goal of running large AI models directly on iPhones without relying on cloud computing. PrismML says its technology can reduce model memory usage by 10 to 15 times, enabling a model with 27 billion parameters to run on iPhone 15 and above, while improving response speed by 6 to 8 times and reducing energy consumption by 3 to 6 times. If the technology matures, Apple could shift more Siri and generative AI functions to run locally, further improving response times, privacy protection, and offline usability, while lowering cloud computing costs. However, industry insiders note that the technology still needs to be validated through large-scale real-world deployments, and its impact on battery life, stability, and long-term performance remains to be seen.
AAPL-0.78%
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned