{"id":52996,"date":"2026-08-25T16:11:54","date_gmt":"2026-08-25T20:11:54","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=52996"},"modified":"2026-08-25T16:12:23","modified_gmt":"2026-08-25T20:12:23","slug":"apple-m6-and-m5-ultra","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2026\/08\/25\/apple-m6-and-m5-ultra\/","title":{"rendered":"Apple M6 and M5 Ultra"},"content":{"rendered":"<p><a href=\"https:\/\/www.apple.com\/newsroom\/2026\/08\/apple-introduces-m6-and-m5-ultra-for-a-big-leap-in-performance-and-ai-compute\/\">Apple<\/a> (<a href=\"https:\/\/www.macrumors.com\/2026\/08\/25\/apple-debuts-m5-ultra\/\">MacRumors M5 Ultra<\/a> and <a href=\"https:\/\/www.macrumors.com\/2026\/08\/25\/apple-reveals-m6\/\">M6<\/a>, <a href=\"https:\/\/news.ycombinator.com\/item?id=49433292\">Hacker News<\/a>):<\/p>\n<blockquote cite=\"https:\/\/www.apple.com\/newsroom\/2026\/08\/apple-introduces-m6-and-m5-ultra-for-a-big-leap-in-performance-and-ai-compute\/\">\n<p>M6 is built using cutting-edge 2 nm process technology, packing greater transistor density into a smaller die for a major leap in performance and power efficiency. M6 also introduces a Dual 16-core Neural Engine, providing up to 2x the peak compute over previous generations to make on-device AI workflows run even faster. System frameworks can automatically utilize both engines simultaneously, enabling applications to see faster model execution.<\/p>\n<p>M6 has a brand-new 12-core CPU complex &mdash; two more cores than M5 &mdash; that consists of 2 super cores, 4 performance cores, and 6 efficiency cores. It delivers the world&rsquo;s fastest single-threaded performance and up to 1.2x faster multithreaded performance as compared to M5, and up to 2.4x faster than M1.<\/p>\n<p>[&#8230;]<\/p>\n<p>M5 Ultra uses UltraFusion to connect two dual-die M5 Max chips to form the quad-die architecture &mdash; a first for Apple silicon. UltraFusion increases the inter-die bandwidth to over 4.4TB\/s and the connection density by over 6x. Together, these ultra-low-latency, high-bandwidth interconnects allow the four dies to behave as a single unified processor. M5 Ultra also features a large up-to-36-core CPU consisting of 12 super cores and 24 performance cores, delivering up to 1.25x higher single-threaded performance and up to 1.3x higher multithreaded performance than M3 Ultra.<\/p>\n<p>M5 Ultra features a next-generation GPU with up to 80 cores, incorporating a Neural Accelerator in each core to offer up to 4.5x the peak GPU compute for AI compared to M3 Ultra and over 6x more than M1 Ultra.<\/p>\n<\/blockquote>\n\n<p><a href=\"https:\/\/news.ycombinator.com\/item?id=49439789\">ghostly_s<\/a>:<\/p>\n<blockquote cite=\"https:\/\/news.ycombinator.com\/item?id=49439789\">\n<p>It was not long ago all the illustrations in an M chip press release were graphs showing it flouncing the competition. Now it&rsquo;s just random screenshots of desktops. Skimming this I didn&rsquo;t see a single claim of performance advantages over competitors. The massive thing Apple still needs to solve is making sure customers don&rsquo;t miss being able to plug the latest greatest GPU into their tower, they should not be resting on their laurels.<\/p>\n<\/blockquote>\n\n<p><a href=\"https:\/\/mastodon.social\/@agiletortoise\/117156694705952366\">Greg Pierce<\/a>:<\/p>\n<blockquote cite=\"https:\/\/mastodon.social\/@agiletortoise\/117156694705952366\">\n<p>I&rsquo;m so old I remember when Apple PR benchmarks were all like &ldquo;Photoshop Gaussian Blur in only 48 seconds!&rdquo;<\/p>\n<\/blockquote>\n\n<p>Previously:<\/p>\n<ul>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2026\/08\/25\/mac-studio-2026\/\">Mac Studio 2026<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2026\/08\/25\/mac-mini-2026\/\">Mac mini 2026<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2026\/03\/27\/goodbye-mac-pro\/\">Goodbye, Mac Pro<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2026\/03\/03\/apple-m5-pro-and-m5-max\/\">Apple M5 Pro and M5 Max<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2025\/10\/15\/apple-m5\/\">Apple M5<\/a><\/li>\n<li><a href=\"https:\/\/mjtsai.com\/blog\/2025\/03\/05\/apple-m3-ultra\/\">Apple M3 Ultra<\/a><\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>Apple (MacRumors M5 Ultra and M6, Hacker News): M6 is built using cutting-edge 2 nm process technology, packing greater transistor density into a smaller die for a major leap in performance and power efficiency. M6 also introduces a Dual 16-core Neural Engine, providing up to 2x the peak compute over previous generations to make on-device [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"apple_news_api_created_at":"2026-08-25T20:11:58Z","apple_news_api_id":"922a4d27-3106-40b3-81ff-e11710813db6","apple_news_api_modified_at":"2026-08-25T20:12:26Z","apple_news_api_revision":"AAAAAAAAAAAAAAAAAAAAAA==","apple_news_api_share_url":"https:\/\/apple.news\/AkipNJzEGQLOB_-EXEIE9tg","apple_news_coverimage":0,"apple_news_coverimage_caption":"","apple_news_is_hidden":false,"apple_news_is_paid":false,"apple_news_is_preview":false,"apple_news_is_sponsored":false,"apple_news_maturity_rating":"","apple_news_metadata":"\"\"","apple_news_pullquote":"","apple_news_pullquote_position":"","apple_news_slug":"","apple_news_sections":"\"\"","apple_news_suppress_video_url":false,"apple_news_use_image_component":false,"footnotes":""},"categories":[2],"tags":[2307,2956,2957,1351,30,260],"class_list":["post-52996","post","type-post","status-publish","format-standard","hentry","category-technology","tag-apple-hardware-announcement","tag-apple-m5-ultra","tag-apple-m6","tag-artificial-intelligence","tag-mac","tag-processors"],"apple_news_notices":[],"_links":{"self":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/52996","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/comments?post=52996"}],"version-history":[{"count":2,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/52996\/revisions"}],"predecessor-version":[{"id":53002,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/52996\/revisions\/53002"}],"wp:attachment":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/media?parent=52996"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/categories?post=52996"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/tags?post=52996"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}