Apple Exploring Ways to Run Much Larger AI Models Directly on iPhones
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.11 Articles
11 Articles
New AI startup could shrink server-sized models for use on iPhones
PrismML, a startup that uses mathematical wizardry to shrink the size of large language models, could be used to bring more advanced AI capabilities to iPhones in the future.Apple wants to bring bigger AI models to the iPhoneThe company has already been able to compress the 54GB Qwen 3.6 model to just 4GB. And, importantly, the technology that it uses doesn't impact the model's performance.Apple is already keen to find ways to shrink LLMs that w…
machash.com
MacDailyNewsApple eyes PrismML to run huge AI models directly on iPhone
Apple is in discussions with PrismML, a Khosla Ventures-backed startup that claims to have achieved a major breakthrough in running exceptionally large AI models directly on iPhones without relying on cloud servers, Aaron Tilley reports for The Information. The company says it has successfully compressed and executed a 27-billion-parameter model on the latest iPhone hardware, marking what it describes as the largest AI model ever run fully on-de…
The AI on the iPhone has always faced a physical limitation that is difficult to circumvent: the amount of RAM available on smartphones. Although Apple's chips are among the most powerful in the market, running artificial intelligence models directly on the device continues to be a huge challenge. After all, modern models often require dozens of gigabytes of memory, something far above the capacity of current iPhones. However, this scenario may …
In March, we downloaded a ChatGPT public server model to the Macbook Pro M5 Max and used the model instead of the traditional server version. The idea behind it was to prove that the M5 Max is already so powerful that the current server variants of the large LLMs will easily also run locally. Also on the previous WWDC keynote it became clear that Apple relies on Local Inference in the medium term, i.e. on the models that can run directly on the …
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
