Apple in talks with startup that shrinks AI models to run on an iPhone
PrismML says its compressed version of Alibaba’s Qwen model uses up to 15 times less memory, potentially advancing Apple’s AI push.
Apple's reported talks with PrismML, a startup focused on compressing AI models, could have implications for the tech giant's artificial intelligence ambitions. The ability to run complex AI models on devices like the iPhone, rather than relying on cloud-based processing, would enhance user experience and potentially drive increased adoption of AI-powered services.
The specific example of PrismML's compressed version of Alibaba's Qwen model, which uses up to 15 times less memory, highlights the advancements being made in model compression. This technology has the potential to unlock new use cases for AI on edge devices, such as smartphones and laptops. For Apple, integrating this technology could enable more sophisticated AI-powered features on its devices, further differentiating its offerings from competitors.
As investors, it's worth watching how Apple's AI strategy evolves in the coming months. A key area to monitor is the company's plans for on-device AI processing, as well as potential partnerships with startups like PrismML. Additionally, the impact of AI advancements on Apple's hardware sales and services revenue will be an important metric to track, particularly as the company continues to navigate the competitive landscape in the tech industry.
Originally reported by cnbc.com. BondNews adds analysis for finance & markets readers.