OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit40m ago 10 of the scariest AI villains in movie history41m ago Maven Robotics wants to steal your robot deployment deal42m ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford45m ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges52m ago 7 Steps to Become a Forward Deployed Engineer in 20261h ago Ramp eyes $60bn valuation three months after $44bn, Bloomberg reports1h ago D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion2h ago Andrew Tulloch, Poster Child for Out-of-Control AI Spending, Reportedly Quits Meta1h ago Mother Horrified When Instagram’s AI Scours Social Media for Invasive Information About Her Young Daughters2h ago Salesforce Unveils Six-Capability Trusted AI Harness for Enterprises2h ago US closes $1.9bn loan to restart the Iowa nuclear plant powering Google2h ago OpenAI Gives US Agencies 50% Off Models, Ending $1 Per Year Deal2h ago 47,000 job listings reveal the engineering roles that AI is creating2h ago

OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit40m ago 10 of the scariest AI villains in movie history41m ago Maven Robotics wants to steal your robot deployment deal42m ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford45m ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges52m ago 7 Steps to Become a Forward Deployed Engineer in 20261h ago Ramp eyes $60bn valuation three months after $44bn, Bloomberg reports1h ago D-Matrix Connects Raptor XPUs to NVIDIA AI Factories via NVLink Fusion2h ago Andrew Tulloch, Poster Child for Out-of-Control AI Spending, Reportedly Quits Meta1h ago Mother Horrified When Instagram’s AI Scours Social Media for Invasive Information About Her Young Daughters2h ago Salesforce Unveils Six-Capability Trusted AI Harness for Enterprises2h ago US closes $1.9bn loan to restart the Iowa nuclear plant powering Google2h ago OpenAI Gives US Agencies 50% Off Models, Ending $1 Per Year Deal2h ago 47,000 job listings reveal the engineering roles that AI is creating2h ago

Machine Learning Dev4 min reading time

Apple is in talks with the startup shrinking a 27B AI model onto an iPhone

The Next WebPublished Jul 15, 2026

Apple is in early discussions with PrismML, a startup that compresses large AI models to run on devices like the iPhone, potentially enabling more on-device AI processing for Siri. PrismML's Bonsai 27B model shrinks Alibaba's Qwen model from 54GB to as little as 3.9GB, allowing it to fit on an iPhone 17 Pro with some performance trade-offs. This technology could reduce latency, cloud costs, and enhance privacy by processing AI tasks locally on Apple devices.

#apple #bonsai-27b #iphone-17-pro #prismml #qwen-model #siri

More in Machine Learning

Machine Learning3 min read

Nvidia and Palantir fine-tune a 30B Nemotron model for Nvidia’s supply chain. It beats a model 18 times its size.

Covered by 3 sources6h ago

Machine Learning6 min read

CoreWeave Puts Field Engineers Inside Customer Teams for Physical AI

Covered by 2 sources2h ago

Machine Learning2 min read

Weatherwatch: AI model beats standard methods at predicting cyclones

The Guardian10h ago