{"id":48838,"date":"2025-08-08T15:14:10","date_gmt":"2025-08-08T19:14:10","guid":{"rendered":"https:\/\/mjtsai.com\/blog\/?p=48838"},"modified":"2025-08-12T14:44:14","modified_gmt":"2025-08-12T18:44:14","slug":"framework-desktop","status":"publish","type":"post","link":"https:\/\/mjtsai.com\/blog\/2025\/08\/08\/framework-desktop\/","title":{"rendered":"Framework Desktop"},"content":{"rendered":"<p><a href=\"https:\/\/world.hey.com\/dhh\/the-framework-desktop-is-a-beast-636fb4ff\">David Heinemeier Hansson<\/a>:<\/p>\n<blockquote cite=\"https:\/\/world.hey.com\/dhh\/the-framework-desktop-is-a-beast-636fb4ff\"><p>It&rsquo;s a solid 40% faster than the M4 Max and 50% faster than the M4 Pro! Now some will say &ldquo;that&rsquo;s just because Docker is faster on Linux,&rdquo; and they&rsquo;re not entirely wrong. Docker runs natively on Linux, so for this test, where the MySQL\/Redis\/ElasticSearch data stores run in Docker while Ruby and the app code runs natively, that&rsquo;s part of the answer. Last I checked, it was about 25% of the difference.<\/p><p>But so what? Docker is an integral part of the workflow for tons of developers.<\/p><p>[&#8230;]<\/p><p>[Multicore performance] Basically matching the M4 Max! [&#8230;] To be fair, the M4s are faster in single-core performance. Apple holds the crown there. It&rsquo;s about 20%.<\/p><p>[&#8230;]<\/p><p>It gets even better when you bring price into the equation, though. The Framework Desktop with 64GB RAM + 2TB NVMe is $1,876. To get a Mac Studio with similar specs &mdash; M4 Max, 64GB RAM, 2TB NVMe &mdash; you&rsquo;ll literally spend nearly twice as much at $3,299! If you go for 128GB RAM, you&rsquo;ll spend $2,276 on the Framework, but $4,099 on the Mac.<\/p><\/blockquote>\n\n<p>See also: <a href=\"https:\/\/www.tomshardware.com\/desktops\/gaming-pcs\/framework-desktop-review\">Andrew E. Freedman<\/a>.<\/p>\n\n<p id=\"framework-desktop-update-2025-08-11\">Update (<a href=\"#framework-desktop-update-2025-08-11\">2025-08-11<\/a>): See also: <a href=\"https:\/\/news.ycombinator.com\/item?id=44841262\">Hacker News<\/a>.<\/p>\n\n<p id=\"framework-desktop-update-2025-08-12\">Update (<a href=\"#framework-desktop-update-2025-08-12\">2025-08-12<\/a>): <a href=\"https:\/\/taoofmac.com\/space\/links\/2025\/08\/10\/2227\">Rui Carmo<\/a>:<\/p>\n<blockquote cite=\"https:\/\/taoofmac.com\/space\/links\/2025\/08\/10\/2227\"><p>I&rsquo;ve been wanting to get my hands on one of these for both the ability to run local AI workloads <em>and<\/em> silent, power-efficient operation&#x2013;and now that the Linux support is coming in the prospect of running a <a href=\"https:\/\/taoofmac.com\/space\/os\/linux\/distributions\/fedora\">Fedora<\/a> desktop on this kind of hardware is appealing enough for me to consider dropping macOS&#x2013;I&rsquo;ve spent the past few years slowly hedging my platform bets, and other than <a href=\"https:\/\/taoofmac.com\/space\/apps\/mail\">Mail.app<\/a> and random compatibilty hassles, it wouldn&rsquo;t be much of a change.<\/p><p>In the long run, APUs like this are the future for PCs of any size. Apple will of course keep improving their silicon, but the premium they charge for memory and storage makes no sense when AMD can match most of their performance for nearly half the going rate.<\/p><\/blockquote>","protected":false},"excerpt":{"rendered":"<p>David Heinemeier Hansson: It&rsquo;s a solid 40% faster than the M4 Max and 50% faster than the M4 Pro! Now some will say &ldquo;that&rsquo;s just because Docker is faster on Linux,&rdquo; and they&rsquo;re not entirely wrong. Docker runs natively on Linux, so for this test, where the MySQL\/Redis\/ElasticSearch data stores run in Docker while Ruby [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"apple_news_api_created_at":"2025-08-08T19:14:12Z","apple_news_api_id":"eb9e1c38-44bb-4927-a497-476eaba9da50","apple_news_api_modified_at":"2025-08-12T18:44:16Z","apple_news_api_revision":"AAAAAAAAAAAAAAAAAAAAAg==","apple_news_api_share_url":"https:\/\/apple.news\/A654cOES7SSekl0duq6naUA","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":[1612,2680,2679,1323,452,448,30,2598,71,287],"class_list":["post-48838","post","type-post","status-publish","format-standard","hentry","category-technology","tag-advanced-micro-devices-amd","tag-apple-m4-max","tag-apple-m4-pro","tag-docker","tag-hardware","tag-linux","tag-mac","tag-macos-15-sequoia","tag-programming","tag-ruby"],"apple_news_notices":[],"_links":{"self":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/48838","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=48838"}],"version-history":[{"count":4,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/48838\/revisions"}],"predecessor-version":[{"id":48868,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/posts\/48838\/revisions\/48868"}],"wp:attachment":[{"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/media?parent=48838"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/categories?post=48838"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mjtsai.com\/blog\/wp-json\/wp\/v2\/tags?post=48838"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}