{"id":13807,"date":"2026-11-17T11:02:45","date_gmt":"2026-11-17T02:02:45","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=13807"},"modified":"2026-11-17T11:11:56","modified_gmt":"2026-11-17T02:11:56","slug":"magnitude-cli-0-2-12-release","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-12-release\/","title":{"rendered":"Magnitude @magnitudedev\/cli@0.2.12 Released"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\">magnitudedev\/magnitude<\/a><\/td>\n<\/tr>\n<tr>\n<td>Version<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/@magnitudedev\/cli@0.2.12\">@magnitudedev\/cli@0.2.12<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-28<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>Apache-2.0<\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p><code>magnitudedev\/magnitude<\/code> is an open-source inference engine that tunes kernels to match the user&#8217;s hardware and runs each model as fast as possible. It runs on Apple Silicon, NVIDIA, AMD, Intel, or CPU-only environments, and is reported to be twice as fast as Ollama. This update, <code>@magnitudedev\/cli@0.2.12<\/code>, significantly improves the installer behavior and includes specification changes for certain model IDs.<\/p>\n<h2>Breaking Changes &amp; Deprecations<\/h2>\n<p>The model ID for <code>Qwen3.8 Flash Next NVFP4<\/code> has been changed. If you are specifying this model directly in commands or configuration files, you need to update it to the new ID.<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th style=\"text-align: left;\">Old Model ID<\/th>\n<th style=\"text-align: left;\">New Model ID<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td style=\"text-align: left;\"><code>qwen3.8-flash-next-nvfp4:gguf:nvfp4<\/code><\/td>\n<td style=\"text-align: left;\"><code>qwen3.8-flash-next:gguf:nvfp4<\/code><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>This change is due to a structural update where <code>Qwen3.8 Flash Next NVFP4<\/code> is now treated as a variant of <code>Qwen3.8 Flash Next<\/code> rather than as a separate model.<\/p>\n<h2>Key Changes<\/h2>\n<h3>Installer Behavior and UX Improvements<\/h3>\n<p>The installation mechanism has been improved across all platforms: macOS, Linux, and Windows. READMEs and installation guides now use a common installation script, making the installation process more streamlined.<\/p>\n<p>Display features for the installer have also been enhanced, showing download speeds and remaining time for each download. Furthermore, the screen no longer flashes white during downloads, and the desktop app now opens automatically upon completion. Even under unstable network conditions, downloads previously failed after 10 minutes, but moving forward they will only fail if &#8220;no data is received for 60 seconds&#8221;, accompanied by a notification.<\/p>\n<p>Per-OS operations have also been optimized. On Windows, silent setup is available once again. Additionally, if Magnitude is running during a download, a mechanism has been introduced to prompt closing the app beforehand rather than failing with an error at the end. On macOS, for environments below macOS 15, instead of forcibly attempting to install an app that will not launch, users are now notified in advance that macOS 15 or later is required. Moreover, on Linux environments that do not use systemd (such as containers or WSL), the server mode option will no longer be displayed.<\/p>\n<h3>Improved Reliability for Linux Server Setup<\/h3>\n<p>Reliability regarding server operations on Linux has been improved. Even if the process is interrupted during server setup, network access is maintained in a valid state so that it remains accessible from other computers. If interrupted, the access key can be displayed again by running <code>magnitude server setup<\/code>.<\/p>\n<p>Additionally, running the <code>magnitude server remove<\/code> command now properly closes the <code>firewalld<\/code> ports opened during setup, ensuring that server features are removed more reliably.<\/p>\n<h3>Application UI\/UX Improvements<\/h3>\n<p>Usability of the chat interface has been enhanced. The chat auto-scroll feature has been improved: if a user scrolls up to read past messages, auto-scroll pauses, and it resumes once scrolled all the way back down.<\/p>\n<p>While model reassessment is underway, previous fit results are now kept on display, preventing the view from reverting to an &#8220;assessing&#8221; state during evaluation. Minor improvements have also been made, such as adding a link to the Docs above Settings in the sidebar.<\/p>\n<p>Regarding hardware support, Intel GPUs are now explicitly listed as supported.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>Intel GPUs are now explicitly listed as supported hardware. This allows users utilizing Intel GPU environments to confirm that they are covered by Magnitude&#8217;s support.<\/p>\n<h2>How to Get It<\/h2>\n<p>Installation procedures using a common installation script are provided for macOS, Linux, and Windows platforms. Refer to the README or installation guide for each platform for details.<\/p>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-10-released-2\/\">Magnitude CLI 0.2.10 Released with Memory Fixes and New Quantizations<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-8-released\/\">Magnitude CLI 0.2.8 Released with VRAM Fixes and Gemma 4 Support<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-7-released\/\">Magnitude CLI 0.2.7 Released: Major Speedups and Fixes<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-17-released\/\">Magnitude CLI v0.2.17 Released with Dynamic Context Scaling<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Follow this tool<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-magnitude-en\/\">Magnitude overview and release history (16 releases tracked)<\/a><\/li>\n<li><strong>Other inference engines and runtimes<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-llama-cpp-en\/\">llama.cpp<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ollama-en\/\">Ollama<\/a> \/ <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-vllm-en\/\">vLLM<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.12\">magnitudedev\/magnitude @magnitudedev\/cli@0.2.12<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Release notes for magnitudedev\/magnitude @magnitudedev\/cli@0.2.12 covering installer improvements, model ID changes, and Linux server setup fixes.<\/p>\n","protected":false},"author":1,"featured_media":13806,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[105],"tags":[2076,163,2791,520,1547,1193],"class_list":["post-13807","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-engines-and-tools","tag-cli-en","tag-gguf-en","tag-magnitude-en","tag-qwen-en","tag-verified","tag--en"],"lang":"en","translations":{"en":13807,"ja":13805},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13807","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=13807"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13807\/revisions"}],"predecessor-version":[{"id":17968,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13807\/revisions\/17968"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/13806"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=13807"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=13807"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=13807"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}