{"id":1227,"date":"2026-06-07T12:11:35","date_gmt":"2026-06-07T02:11:35","guid":{"rendered":"https:\/\/www.reefwing.com.au\/?p=1227"},"modified":"2026-06-07T12:11:37","modified_gmt":"2026-06-07T02:11:37","slug":"squeezing-ai-into-your-pocket","status":"publish","type":"post","link":"https:\/\/www.reefwing.com.au\/?p=1227","title":{"rendered":"Squeezing AI into your Pocket"},"content":{"rendered":"\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/www.reefwing.com.au\/wp-content\/uploads\/2026\/06\/reefwing_An_ultra-close_macro_photograph_of_a_single_processo_f9c49ce6-46b7-4092-ad15-7e2cc49efbb8_1.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"1024\" src=\"https:\/\/www.reefwing.com.au\/wp-content\/uploads\/2026\/06\/reefwing_An_ultra-close_macro_photograph_of_a_single_processo_f9c49ce6-46b7-4092-ad15-7e2cc49efbb8_1.png\" alt=\"\" class=\"wp-image-1228\" srcset=\"https:\/\/www.reefwing.com.au\/wp-content\/uploads\/2026\/06\/reefwing_An_ultra-close_macro_photograph_of_a_single_processo_f9c49ce6-46b7-4092-ad15-7e2cc49efbb8_1.png 1024w, https:\/\/www.reefwing.com.au\/wp-content\/uploads\/2026\/06\/reefwing_An_ultra-close_macro_photograph_of_a_single_processo_f9c49ce6-46b7-4092-ad15-7e2cc49efbb8_1-300x300.png 300w, https:\/\/www.reefwing.com.au\/wp-content\/uploads\/2026\/06\/reefwing_An_ultra-close_macro_photograph_of_a_single_processo_f9c49ce6-46b7-4092-ad15-7e2cc49efbb8_1-150x150.png 150w, https:\/\/www.reefwing.com.au\/wp-content\/uploads\/2026\/06\/reefwing_An_ultra-close_macro_photograph_of_a_single_processo_f9c49ce6-46b7-4092-ad15-7e2cc49efbb8_1-768x768.png 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/a><\/figure>\n\n\n\n<p>By 2026, language models have moved off the cloud and onto the device in your pocket. What was a research demonstration two years ago is now a routine engineering capability, and the centre of gravity for artificial intelligence has begun to migrate from distant data centres to local silicon.<\/p>\n\n\n\n<p>The episode traces the four engineering moves that made this possible. Quantization, which shrinks a model by storing its parameters with less precision. Optimized key-value caches, which let a model hold a long conversation without exhausting memory. Neural Processing Units, the dedicated AI accelerators now standard in flagship phones. And specialized frameworks such as LiteRT-LM and llama.cpp, which finally make all three usable from a single application.<\/p>\n\n\n\n<p>The consequences reach further than performance figures. Privacy becomes the default rather than a feature, because data never leaves the device. The cost structure of AI applications changes, because there are no per-query cloud fees. And the link between training capital and deployment capability begins to decouple, opening the door for small teams to ship genuine intelligence on hardware they already control.<\/p>\n\n\n\n<p><a href=\"https:\/\/www.buzzsprout.com\/2429696\/episodes\/19252675\">Listen to the Podcast&#8230;<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>By 2026, language models have moved off the cloud and onto the device in your pocket. What was a research demonstration two years ago is now a routine engineering capability, and the centre of gravity for artificial intelligence has begun to migrate from distant data centres to local silicon. The episode traces the four engineering [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_genesis_hide_title":false,"_genesis_hide_breadcrumbs":false,"_genesis_hide_singular_image":false,"_genesis_hide_footer_widgets":false,"_genesis_custom_body_class":"","_genesis_custom_post_class":"","_genesis_layout":"","_wp_convertkit_post_meta":{"form":"-1","landing_page":"0","tag":"0","restrict_content":"0"},"footnotes":""},"categories":[49,45,43],"tags":[69,70],"class_list":{"0":"post-1227","1":"post","2":"type-post","3":"status-publish","4":"format-standard","6":"category-ai","7":"category-embedded","8":"category-robotics","9":"tag-embedded-ai","10":"tag-podcast","11":"entry"},"_links":{"self":[{"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=\/wp\/v2\/posts\/1227","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1227"}],"version-history":[{"count":1,"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=\/wp\/v2\/posts\/1227\/revisions"}],"predecessor-version":[{"id":1229,"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=\/wp\/v2\/posts\/1227\/revisions\/1229"}],"wp:attachment":[{"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1227"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1227"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.reefwing.com.au\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1227"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}