{"id":289502,"date":"2026-07-14T15:30:00","date_gmt":"2026-07-14T19:30:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/07\/14\/privacy-focused-apple-in-talks-with-startup-to-run-more-powerful-ai-models-directly-on-devices\/"},"modified":"2026-07-14T16:15:11","modified_gmt":"2026-07-14T20:15:11","slug":"privacy-focused-apple-in-talks-with-startup-to-run-more-powerful-ai-models-directly-on-devices","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/07\/14\/privacy-focused-apple-in-talks-with-startup-to-run-more-powerful-ai-models-directly-on-devices\/","title":{"rendered":"Privacy-focused Apple in talks with startup to run more powerful AI models directly on devices"},"content":{"rendered":"

Privacy-focused Apple in talks with startup to run more powerful AI models directly on devices<\/a><\/p>\n

https:\/\/macdailynews.com\/2026\/07\/14\/privacy-focused-apple-in-talks-with-startup-to-run-more-powerful-ai-models-directly-on-devices\/<\/a><\/p>\n

Publish Date: 2026-07-14 15:30:00<\/a><\/p>\n

Source Domain: macdailynews.com<\/a><\/p>\n

\t\t\t\t\t\tApple\u2019s all-new Siri AI. An even more capable AI assistant with expanded intelligence to be more helpful every day.<\/p>\n

Apple is exploring new ways to keep AI processing on users\u2019 devices, prioritizing speed, privacy, and reduced reliance on the cloud. The company is in early discussions with PrismML, a startup developing technology that dramatically compresses large AI models to fit and run efficiently on iPhones.<\/p>\n

According to PrismML CEO Babak Hassibi, who spoke to CNBC, Apple and other companies have been evaluating the startup\u2019s models, measuring their speed, energy efficiency, and performance on devices. \u201cThey\u2019re really evaluating our technology right now,\u201d Hassibi said of Apple. He described the discussions as very early but noted that \u201cthings are progressing nicely.\u201d<\/p>\n

Shrinking Massive Models for Everyday Devices<\/strong><\/p>\n

PrismML, a Khosla Ventures-backed spinout from the California Institute of Technology, recently released compressed versions of Alibaba\u2019s open-source Qwen model. The company reduced the model from roughly 54 GB to less than 4 GB, enabling all 27 billion parameters to run on an iPhone 15 or newer.<\/p>\n

The compression technique simplifies how internal information is stored\u2014reducing values from 16 bits to just one or three possible values. PrismML claims the compressed models use 10 to 15 times less memory, generate responses six to eight times faster, and consume three to six times less energy than conventional versions.<\/p>\n

Hassibi acknowledged a small performance trade-off: \u201cPrismML\u2019s models typically lose a few percentage points of overall performance, with factual recall weakening before skills such as reasoning, math and coding.\u201d Despite this, the company is releasing two compressed versions for free, designed to run on iPhones, MacBooks, and Nvidia-powered PCs.<\/p>\n

Boosting Siri and On-Device Capabilities<\/strong><\/p>\n

This development aligns closely with Apple\u2019s ongoing efforts to enhance Siri. Just before PrismML\u2019s release, Apple…<\/p>\n

Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Privacy-focused Apple in talks with startup to run more powerful AI models directly on devices…<\/p>\n","protected":false},"author":1,"featured_media":289503,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/macdailynews.com\/wp-content\/uploads\/2026\/06\/260611_siri_ai_02.png","fifu_image_alt":"","footnotes":""},"categories":[16],"tags":[],"class_list":["post-289502","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-privacy"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/289502"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=289502"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/289502\/revisions"}],"predecessor-version":[{"id":289504,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/289502\/revisions\/289504"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/289503"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=289502"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=289502"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=289502"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}