Apple reportedly in talks with PrismML to squeeze massive AI models onto iPhones

Apple is reportedly in early negotiations with PrismML, a small AI startup backed by Khosla Ventures, to explore technology that could allow significantly larger AI models to run entirely on an iPhone. No cloud servers, no data leaving your pocket.

What PrismML actually does

PrismML’s headline trick is compressing Alibaba’s Qwen 3.6 model, a 27-billion-parameter beast that normally requires roughly 54GB of memory, down to under 4GB. That makes it small enough to run actively on an iPhone 17 Pro without phoning home to external servers.

The company uses what it describes as ultra-low-bit weight compression, a technique that reduces the precision of each parameter’s numerical representation while preserving the model’s overall performance. Vinod Khosla, the venture capital legend whose firm led PrismML’s $16.25 million seed round in early 2026, called the approach a “mathematical breakthrough.”

PrismML has announced plans to open-source its compressed model on July 14, 2026. The startup is already looking beyond current capabilities, with ambitions to eventually compress trillion-parameter models for edge deployment.

Why Apple cares

Apple’s current on-device AI model, the AFM 3 Core Advanced, has 20 billion parameters on paper. But it’s sparsely activated, meaning only 1 to 4 billion parameters fire at any given time.

The discussions with PrismML fit into a broader pattern. Apple has previously acquired DarwinAI and has held negotiations with companies like Google and OpenAI to bolster its AI capabilities. The current talks, reported on July 9-10, 2026, coincide with ongoing updates to iOS 27 that are focused on enhancing Siri and the broader Apple Intelligence suite.

The crypto and market angle

PrismML’s $16.25 million seed round is modest by Silicon Valley standards. But the technology’s potential to reshape how and where AI runs makes it disproportionately significant. Investors should watch the July 14 open-source release closely, because once this compression technology is publicly available, the race to deploy it won’t be limited to Apple.

Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our Editorial Policy.