{"id":289663,"date":"2026-07-15T03:39:00","date_gmt":"2026-07-15T07:39:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/07\/15\/apple-in-talks-with-startup-firm-to-shrink-ai-models-to-run-directly-on-iphone\/"},"modified":"2026-07-15T04:20:07","modified_gmt":"2026-07-15T08:20:07","slug":"apple-in-talks-with-startup-firm-to-shrink-ai-models-to-run-directly-on-iphone","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/07\/15\/apple-in-talks-with-startup-firm-to-shrink-ai-models-to-run-directly-on-iphone\/","title":{"rendered":"Apple in talks with startup firm to shrink AI models to run directly on iPhone"},"content":{"rendered":"<p><a href=\"https:\/\/www.thestandard.com.hk\/finance\/article\/337291\/Apple-in-talks-with-startup-firm-to-shrink-AI-models-to-run-directly-on-iPhone\">Apple in talks with startup firm to shrink AI models to run directly on iPhone<\/a><\/p>\n<p><a href=\"https:\/\/www.thestandard.com.hk\/finance\/article\/337291\/Apple-in-talks-with-startup-firm-to-shrink-AI-models-to-run-directly-on-iPhone\">https:\/\/www.thestandard.com.hk\/finance\/article\/337291\/Apple-in-talks-with-startup-firm-to-shrink-AI-models-to-run-directly-on-iPhone<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-07-15 03:39:00<\/a><\/p>\n<p>Source Domain: <a href=\"www.thestandard.com.hk\">www.thestandard.com.hk<\/a><\/p>\n<p><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">Apple is reportedly in talks with Silicon Valley startup PrismML to bring high-performance large AI models to the iPhone through model compression.<\/span><\/span><\/p>\n<p style=\"text-align:justify;margin-bottom:19px\"><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">PrismML chief executive Babak Hassibi told CNBC that the company can shrink AI models to a size sufficient to run directly on the iPhone. Apple has been evaluating the company&#8217;s technology and measuring its speed, energy efficiency, and performance on devices.<\/span><\/span><\/p>\n<p style=\"text-align:justify;margin-bottom:19px\"><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">PrismML released a compressed version of Alibaba&#8217;s (9988) open-source Qwen model on <\/span><\/span><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">Tuesday, reducing the model from 54GB to 4GB, achieving a memory usage reduction of over 90 percent and allowing all 27 billion parameters to run on an iPhone 15 or newer models.<\/span><\/span><\/p>\n<p style=\"text-align:justify;margin-bottom:19px\"><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">Hassibi acknowledged a trade-off, as efficiency gains from compression come at the cost of model accuracy. The PrismML models typically lose several percentage points of overall performance, with factual recall weakening before reasoning, mathematical, and programming abilities.<\/span><\/span><\/p>\n<p style=\"text-align:justify;margin-bottom:19px\"><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">Apple has launched a new version of Siri on Monday, in bid to compete with companies like OpenAI and Anthropic, while keeping more personal information and AI processing on-device.<\/span><\/span><\/p>\n<p style=\"text-align:justify;margin-bottom:19px\"><span style=\"font-weight:400;font-variant:normal;white-space:pre-wrap\"><span style=\"font-style:normal\">While Apple can send complex requests to cloud-based models, running AI directly on the iPhone would reduce the delay associated, lower cloud-computing costs and support the company\u2019s privacy pitch.<\/span><\/span><\/p>\n<p>\u00a0<\/p>\n<p><a href=\"https:\/\/www.thestandard.com.hk\/finance\/article\/337291\/Apple-in-talks-with-startup-firm-to-shrink-AI-models-to-run-directly-on-iPhone\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Apple in talks with startup firm to shrink AI models to run directly on iPhone&#8230;<\/p>\n","protected":false},"author":1,"featured_media":289664,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/image.hkstandard.com.hk\/f\/1200p0\/0x0\/100\/none\/5d6e8f10c81e6face75e4afb6eda5dc2\/2026-07\/2026-07-10T211010Z_2026948577_RC2P3EAEIF7R_RTRMADP_3_APPLE-OPENAI-LAWSUIT.jpg","fifu_image_alt":"","footnotes":""},"categories":[120],"tags":[74],"class_list":["post-289663","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-iphone","tag-iphone-15"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/289663"}],"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=289663"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/289663\/revisions"}],"predecessor-version":[{"id":289665,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/289663\/revisions\/289665"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/289664"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=289663"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=289663"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=289663"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}