Apple Exploring Ways to Run Much Larger AI Models Directly on iPhones

PrismML Tech: Capability to compress models so all parameters remain active on mobile, rather than using sparse architectures.
Current Baseline: Apple's current AFM 3 Core Advanced model is 20B parameters but sparse, only using 1-4B active at once.
Potential: Running dense models allows for better reasoning capabilities in local Siri and system-wide intelligence features.
Strategic Shift: Moving more intelligence on-device directly reduces server-side operational costs.

Apple has held meetings with PrismML about ways it could use the startup's technology to run much larger AI models directly on iPhones, according to The Information.

The report said PrismML has managed to shrink down Alibaba's open-source large language model Qwen 3.6 to run entirely on an iPhone 17 Pro. The model has 27 billion parameters, which is larger than Apple's on-device AFM 3 Core Advanced model with 20 billion parameters. Apple's model powers iOS 27 enhancements such as Siri AI's more expressive voices and improved systemwide dictation on iPhone 17 Pro and iPhone Air models.

Unlike with AFM 3 Core Advanced, all of Qwen 3.6's parameters can be active at the same time.

"One new on-device Apple model has 20 billion parameters but uses a so-called sparse architecture, in which only 1 billion to 4 billion parameters are active at a time," the report said, in reference to AFM 3 Core Advanced. "In the case of PrismML's on-device model, all 27 billion parameters are active at the same time."

Larger models running directly on iPhones would allow for more Apple Intelligence features to run on device instead of on Apple's Private Cloud Compute servers, which could reduce Apple's costs and further enhance user privacy.