{"id":1274,"date":"2026-09-17T16:56:56","date_gmt":"2026-09-17T07:56:56","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/engine-ggml-en\/"},"modified":"2026-10-28T20:36:47","modified_gmt":"2026-10-28T11:36:47","slug":"engine-ggml-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-ggml-en\/","title":{"rendered":"ggml: Releases and Overview"},"content":{"rendered":"<p>Tensor library underlying llama.cpp and whisper.cpp. The GGUF format and quantization kernels live here.<\/p>\n<p><em>Category: Quantization, model formats and fine-tuning. 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\/ggml-org\/ggml\">ggml-org\/ggml<\/a><\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>MIT<\/td>\n<\/tr>\n<tr>\n<td>Main language<\/td>\n<td>C++<\/td>\n<\/tr>\n<tr>\n<td>GitHub stars<\/td>\n<td>15,363 (as of 2026-09-17)<\/td>\n<\/tr>\n<tr>\n<td>Latest release<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.28.0\">v0.28.0<\/a> (2026-10-28)<\/td>\n<\/tr>\n<tr>\n<td>Install \/ docs<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml#readme\">official documentation<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>The project describes itself as: \u201cTensor library for machine learning\u201d<\/p>\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>v0.28.0<\/td>\n<td>2026-10-28<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.28.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.27.0<\/td>\n<td>2026-10-15<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.27.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.26.0<\/td>\n<td>2026-10-05<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.26.0\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/ggml-v0260-released\/\">ggml v0.26.0 Released with Sparse Flash Attention &amp; New Backends<\/a><\/td>\n<\/tr>\n<tr>\n<td>v0.25.3<\/td>\n<td>2026-09-25<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.25.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.25.2<\/td>\n<td>2026-09-24<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.25.2\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/24\/ggml-v0-25-2-released\/\">ggml v0.25.2 Released with Hardware Backend Optimizations<\/a><\/td>\n<\/tr>\n<tr>\n<td>v0.25.1<\/td>\n<td>2026-09-24<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.25.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.25.0<\/td>\n<td>2026-09-23<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.25.0\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/23\/ggml-v025-0-released\/\">ggml v0.25.0 Released: FlashAttention and MoE Optimizations<\/a><\/td>\n<\/tr>\n<tr>\n<td>v0.24.0<\/td>\n<td>2026-09-14<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.24.0\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/14\/ggml-v0-24-0-released-2\/\">ggml v0.24.0 Released with Backend Improvements and API Updates<\/a><\/td>\n<\/tr>\n<tr>\n<td>v0.23.0<\/td>\n<td>2026-09-04<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.23.0\">GitHub<\/a><\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/06\/ggml-v0230-release\/\">Japanese article only<\/a><\/td>\n<\/tr>\n<tr>\n<td>v0.22.0<\/td>\n<td>2026-08-25<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.22.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.21.0<\/td>\n<td>2026-08-21<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.21.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.20.2<\/td>\n<td>2026-08-18<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.20.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.20.1<\/td>\n<td>2026-08-17<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.20.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.20.0<\/td>\n<td>2026-08-15<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.20.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.19.0<\/td>\n<td>2026-08-07<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.19.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.18.1<\/td>\n<td>2026-08-04<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.18.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.18.0<\/td>\n<td>2026-07-30<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.18.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.17.0<\/td>\n<td>2026-07-17<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.17.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.16.0<\/td>\n<td>2026-07-10<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.16.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.15.3<\/td>\n<td>2026-06-26<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.15.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.15.2<\/td>\n<td>2026-06-19<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.15.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.15.1<\/td>\n<td>2026-06-12<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.15.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.15.0<\/td>\n<td>2026-06-12<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.15.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.14.0<\/td>\n<td>2026-06-08<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.14.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.13.1<\/td>\n<td>2026-05-29<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.13.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.12.1<\/td>\n<td>2026-05-26<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.12.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.13.0<\/td>\n<td>2026-05-26<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.13.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.12.0<\/td>\n<td>2026-05-16<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.12.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.11.1<\/td>\n<td>2026-05-11<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.11.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.11.0<\/td>\n<td>2026-05-05<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.11.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.10.2<\/td>\n<td>2026-05-02<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.10.2\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.10.1<\/td>\n<td>2026-04-30<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.10.1\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.10.0<\/td>\n<td>2026-04-21<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.10.0\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.11<\/td>\n<td>2026-04-02<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.11\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.10<\/td>\n<td>2026-04-02<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.10\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.9<\/td>\n<td>2026-03-31<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.9\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.8<\/td>\n<td>2026-03-17<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.8\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.7<\/td>\n<td>2026-02-16<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.7\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.6<\/td>\n<td>2026-02-07<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.6\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.5<\/td>\n<td>2026-01-01<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.5\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.4<\/td>\n<td>2025-09-30<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.4\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.3<\/td>\n<td>2025-09-25<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.3\">GitHub<\/a><\/td>\n<td>\u2014<\/td>\n<\/tr>\n<tr>\n<td>v0.9.1<\/td>\n<td>2025-09-20<\/td>\n<td><a href=\"https:\/\/github.com\/ggml-org\/ggml\/releases\/tag\/v0.9.1\">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>2026-10-06 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/06\/ggml-v0260-released\/\">ggml v0.26.0 Released with Sparse Flash Attention &amp; New Backends<\/a><\/li>\n<li>2026-09-24 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/24\/ggml-v0-25-2-released\/\">ggml v0.25.2 Released with Hardware Backend Optimizations<\/a><\/li>\n<li>2026-09-23 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/23\/ggml-v025-0-released\/\">ggml v0.25.0 Released: FlashAttention and MoE Optimizations<\/a><\/li>\n<li>2026-09-14 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/14\/ggml-v0-24-0-released-2\/\">ggml v0.24.0 Released with Backend Improvements and API Updates<\/a><\/li>\n<li>2026-09-06 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/06\/ggml-v0230-release\/\">Japanese article only<\/a><\/li>\n<\/ul>\n<p><em>Last updated 2026-10-28 (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>Tensor library underlying llama.cpp and whisper.cpp. The GGUF format and quantization kernels live here. Category: Quantization, model formats and fine-tuning. Part of our engine and tool tracker. At a Glance Item Value Repository ggml-org\/ggml License MIT Main language C++ GitHub stars 15,363 (as of 2026-09-17) Latest release v0.28.0 (2026-10-28) Install \/ docs official documentation The [&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-1274","page","type-page","status-publish","hentry"],"lang":"en","translations":{"en":1274,"ja":1272},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1274","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=1274"}],"version-history":[{"count":12,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1274\/revisions"}],"predecessor-version":[{"id":13963,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/pages\/1274\/revisions\/13963"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=1274"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}