{"id":21891,"date":"2024-10-24T09:57:23","date_gmt":"2024-10-24T01:57:23","guid":{"rendered":"https:\/\/www.1ai.net\/?p=21891"},"modified":"2024-10-24T09:57:23","modified_gmt":"2024-10-24T01:57:23","slug":"%e8%8d%a3%e8%80%80-magicos-9-0-%e5%8d%87%e7%ba%a7%e6%94%af%e6%8c%81-30-%e4%ba%bf%e5%8f%82%e6%95%b0%e7%ab%af%e4%be%a7%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b%ef%bc%9a%e5%8a%9f%e8%80%97%e4%b8%8b","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/21891.html","title":{"rendered":"Honor MagicOS 9.0 Upgrade Supports 3 Billion Parameters End-Side Large Language Model: Power Consumption Drops by 80%, Memory Usage Reduced by 1.6GB"},"content":{"rendered":"<p>October 23rd.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%8d%a3%e8%80%80\" title=\"[Sees articles with [Glory] labels]\" target=\"_blank\" >glory<\/a>Officially released today <a href=\"https:\/\/www.1ai.net\/en\/tag\/magicos\" title=\"_Other Organiser\" target=\"_blank\" >MagicOS<\/a> 9.0, which is claimed to be \"<strong>The industry's first personalized, full-scene AI operating system equipped with intelligent bodies<\/strong>\u201d.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-21892\" title=\"9ceec74ej00slu82j0024d000v900afp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/10\/9ceec74ej00slu82j0024d000v900afp.jpg\" alt=\"9ceec74ej00slu82j0024d000v900afp\" width=\"1125\" height=\"375\" \/><\/p>\n<p>In MagicOS 9.0, MagicOS new magic model family is upgraded to support flexible deployment of end-cloud resources and different devices, with the following versions:<\/p>\n<ul>\n<li>5 million parametric image models, end-side deployment, full range of support<\/li>\n<li>40 Million Parametric Images Large Models, End-Side Deployment, Mid-High End Series<\/li>\n<li><strong>3 billion parameters<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [large language model]]\" target=\"_blank\" >Large Language Model<\/a>End-side deployment, mid- to high-end series<\/strong><\/li>\n<li>1 billion parameter multimodal large model, end-side deployment, mid- to high-end series<\/li>\n<li>15 million parameter speech macromodel, end-side deployment, full range support<\/li>\n<\/ul>\n<p>Honor says the MagicOS 9.0 upgrade supports a 3 billion parameter end-side grand language model, compared to the 7 billion parameter magic grand model of MagicOS 8.0.<strong>Load speed increase 77%, word out speed increase 500%, power consumption decrease 80%<\/strong>. In addition, the new version of the Big Model has a 1.6GB smaller memory footprint and a 1.8GB smaller storage footprint.<\/p>","protected":false},"excerpt":{"rendered":"<p>October 23 news, glory today officially released MagicOS 9.0, said to be \"the industry's first personalized full-scene AI operating system equipped with intelligent body\". In MagicOS 9.0, MagicOS new magic big model family ushered in the upgrade, support for the end of the cloud resources flexible deployment, different devices flexible deployment, with each version as follows: 5 million parameter image big model, end-side deployment, the whole series support 40 million parameter image big model, end-side deployment, the high-end series of 3 billion parameter big language model, end-side deployment, the high-end series 1 billion Parametric multimodal macromodels, side-by-side deployment, 15 million parametric speech macromodels for mid-range and high-end series, side-by-side deployment, full range of support Pride says Magi<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[4716,706,908],"collection":[],"class_list":["post-21891","post","type-post","status-publish","format-standard","hentry","category-news","tag-magicos","tag-706","tag-908"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/21891","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=21891"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/21891\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=21891"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=21891"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=21891"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=21891"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}