{"id":9238,"date":"2026-10-03T00:19:40","date_gmt":"2026-10-02T15:19:40","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/engine-magnitude-en\/"},"modified":"2026-11-17T11:06:20","modified_gmt":"2026-11-17T02:06:20","slug":"engine-magnitude-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-magnitude-en\/","title":{"rendered":"Magnitude: Releases and Overview"},"content":{"rendered":"<p>Open-source inference engine written in Rust (Apache-2.0) that compiles and tunes its kernels on the device it runs on. The project reports up to 2x faster than llama.cpp on Metal and CUDA; in our CPU-only measurement it was about 21x slower.<\/p>\n<p><em>Category: Inference engines and runtimes. Part of our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engines-en\/\">engine and tool tracker<\/a>.<\/em><\/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>Latest release<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.17\">@magnitudedev\/cli@0.2.17<\/a> (2026-11-09)<\/td>\n<\/tr>\n<tr>\n<td>Install \/ docs<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude#readme\">official documentation<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h2>Release History<\/h2>\n<p><em>Compiled by Local Model Watch from the project&#8217;s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.<\/em><\/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>Version<\/th>\n<th>Released<\/th>\n<th>Release notes<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>@magnitudedev\/cli@0.2.17<\/td>\n<td>2026-11-09<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.17\">GitHub<\/a><\/td>\n<td><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><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.16<\/td>\n<td>2026-11-04<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.16\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-0-2-16-released\/\">Magnitude v0.2.16 Released: Faster Parallel Requests and Docker<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.15<\/td>\n<td>2026-10-30<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.15\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.14<\/td>\n<td>2026-10-29<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.14\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-14-released\/\">Magnitude CLI 0.2.14 Released: Faster CPU Decoding and More<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.13<\/td>\n<td>2026-10-28<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.13\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.12<\/td>\n<td>2026-10-28<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.12\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-12-release\/\">Magnitude @magnitudedev\/cli@0.2.12 Released<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.11<\/td>\n<td>2026-10-26<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.11\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-11-released\/\">Magnitude CLI 0.2.11 Released with Custom GGUF Support<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.10<\/td>\n<td>2026-10-20<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.10\">GitHub<\/a><\/td>\n<td><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><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.9<\/td>\n<td>2026-10-15<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.9\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-9-released\/\">Magnitude @magnitudedev\/cli@0.2.9 Released<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.8<\/td>\n<td>2026-10-13<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.8\">GitHub<\/a><\/td>\n<td><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><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.7<\/td>\n<td>2026-10-12<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.7\">GitHub<\/a><\/td>\n<td><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><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.6<\/td>\n<td>2026-10-06<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.6\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/magnitudedev-magnitude-026-released\/\">magnitudedev\/magnitude v0.2.6 Released: Major Mac Speedups<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.5<\/td>\n<td>2026-10-03<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.5\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/03\/magnitude-cli-v0-2-5-released\/\">Magnitude CLI v0.2.5 Released: M5 Mac &amp; MoE Speedups<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.4<\/td>\n<td>2026-10-02<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.4\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/03\/magnitude-0-2-4-released\/\">Magnitude 0.2.4 Released: Faster Inference and Lower Memory<\/a><\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.3<\/td>\n<td>2026-10-01<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>@magnitudedev\/cli@0.2.2<\/td>\n<td>2026-10-01<\/td>\n<td><a href=\"https:\/\/github.com\/magnitudedev\/magnitude\/releases\/tag\/%40magnitudedev\/cli%400.2.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h2>Articles on Local Model Watch<\/h2>\n<ul>\n<li>2026-11-17 <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<li>2026-11-17 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-0-2-16-released\/\">Magnitude v0.2.16 Released: Faster Parallel Requests and Docker<\/a><\/li>\n<li>2026-11-17 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-14-released\/\">Magnitude CLI 0.2.14 Released: Faster CPU Decoding and More<\/a><\/li>\n<li>2026-11-17 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-12-release\/\">Magnitude @magnitudedev\/cli@0.2.12 Released<\/a><\/li>\n<li>2026-11-17 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-11-released\/\">Magnitude CLI 0.2.11 Released with Custom GGUF Support<\/a><\/li>\n<li>2026-11-17 <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>2026-11-17 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/magnitude-cli-0-2-9-released\/\">Magnitude @magnitudedev\/cli@0.2.9 Released<\/a><\/li>\n<li>2026-11-17 <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>2026-11-17 <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>2026-10-06 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/magnitudedev-magnitude-026-released\/\">magnitudedev\/magnitude v0.2.6 Released: Major Mac Speedups<\/a><\/li>\n<li>2026-10-03 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/03\/magnitude-cli-v0-2-5-released\/\">Magnitude CLI v0.2.5 Released: M5 Mac &amp; MoE Speedups<\/a><\/li>\n<li>2026-10-03 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/03\/magnitude-0-2-4-released\/\">Magnitude 0.2.4 Released: Faster Inference and Lower Memory<\/a><\/li>\n<\/ul>\n<p><em>Last updated 2026-11-17 (JST). Facts above come from the GitHub API; the one-paragraph summary was written by the site&#8217;s operator with the help of AI.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Open-source inference engine written in Rust (Apache-2.0) that compiles and tunes its kernels on the device it runs on. The project reports up to 2x faster than llama.cpp on Metal and CUDA; in our CPU-only measurement it was about 21x slower. Category: Inference engines and runtimes. Part of our engine and tool tracker. At a [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-9238","page","type-page","status-publish","hentry"],"lang":"en","translations":{"en":9238,"ja":9237},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/9238","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/page"}],"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=9238"}],"version-history":[{"count":14,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/9238\/revisions"}],"predecessor-version":[{"id":17440,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/9238\/revisions\/17440"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=9238"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}