Apple is reportedly interested in PrismML, a startup that enables advanced AI models to operate on iPhones without servers. The technology, which compresses large models like Qwen 3.6, could enhance on-device AI capabilities for Apple devices.
Apple is reportedly considering PrismML's technology, which focuses on enabling large AI models to run directly on mobile devices. This would eliminate the need for server-based processing, a significant leap in mobile AI capabilities.
PrismML has successfully compressed the Qwen 3.6 model, developed by Alibaba, allowing it to function on the iPhone 17 Pro. This model, which features 27 billion parameters, is designed for tasks requiring complex data processing, surpassing existing mobile models that typically utilize fewer parameters.
The discussions between Apple and PrismML suggest a strategic effort to enhance its AI offerings. Apple's recent acquisition of Q.ai for $2 billion indicates its commitment to investing in AI advancements. The integration of PrismML's technology could play a crucial role in evolving Apple's AI capabilities, particularly with the upcoming release of a modernized Siri in iOS 27.
PrismML is expected to release its open-source model on July 14, which will further demonstrate its capabilities and potentially attract more interest from major technology companies. This could accelerate user adoption of on-device AI functionalities.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
Apple is reportedly interested in PrismML, a startup that enables advanced AI models to operate on iPhones without servers. The technology, which compresses large models like Qwen 3.6, could enhance on-device AI capabilities for Apple devices.