{"id":346,"date":"2026-04-04T00:00:00","date_gmt":"2026-04-04T00:00:00","guid":{"rendered":"https:\/\/wordpress.securinsight.ca\/index.php\/2026\/04\/04\/workers-ai-google-gemma-4-26b-a4b-now-available-on-workers-ai-3\/"},"modified":"2026-04-04T00:00:00","modified_gmt":"2026-04-04T00:00:00","slug":"workers-ai-google-gemma-4-26b-a4b-now-available-on-workers-ai-3","status":"publish","type":"post","link":"https:\/\/wordpress.securinsight.ca\/index.php\/2026\/04\/04\/workers-ai-google-gemma-4-26b-a4b-now-available-on-workers-ai-3\/","title":{"rendered":"Workers AI &#8211; Google Gemma 4 26B A4B now available on Workers AI"},"content":{"rendered":"<p>We are partnering with Google to bring <a href=\"https:\/\/developers.cloudflare.com\/workers-ai\/models\/gemma-4-26b-a4b-it\/\"><code>@cf\/google\/gemma-4-26b-a4b-it<\/code><\/a> to Workers AI. Gemma 4 26B A4B is a Mixture-of-Experts (MoE) model built from Gemini 3 research, with 26B total parameters and only 4B active per forward pass. By activating a small subset of parameters during inference, the model runs almost as fast as a 4B-parameter model while delivering the quality of a much larger one.<\/p>\n<p>Gemma 4 is Google&#8217;s most capable family of open models, designed to maximize intelligence-per-parameter.<\/p>\n<h4>Key capabilities<\/h4>\n<ul>\n<li><strong>Mixture-of-Experts architecture<\/strong> with 8 active experts out of 128 total (plus 1 shared expert), delivering frontier-level performance at a fraction of the compute cost of dense models<\/li>\n<li><strong>256,000 token context window<\/strong> for retaining full conversation history, tool definitions, and long documents across extended sessions<\/li>\n<li><strong>Built-in thinking mode<\/strong> that lets the model reason step-by-step before answering, improving accuracy on complex tasks<\/li>\n<li><strong>Vision understanding<\/strong> for object detection, document and PDF parsing, screen and UI understanding, chart comprehension, OCR (including multilingual), and handwriting recognition, with support for variable aspect ratios and resolutions<\/li>\n<li><strong>Function calling<\/strong> with native support for structured tool use, enabling agentic workflows and multi-step planning<\/li>\n<li><strong>Multilingual<\/strong> with out-of-the-box support for 35+ languages, pre-trained on 140+ languages<\/li>\n<li><strong>Coding<\/strong> for code generation, completion, and correction<\/li>\n<\/ul>\n<p>Use Gemma 4 26B A4B through the <a href=\"https:\/\/developers.cloudflare.com\/workers-ai\/configuration\/bindings\/\">Workers AI binding<\/a> (<code>env.AI.run()<\/code>), the REST API at <code>\/run<\/code> or <code>\/v1\/chat\/completions<\/code>, or the <a href=\"https:\/\/developers.cloudflare.com\/workers-ai\/configuration\/open-ai-compatibility\/\">OpenAI-compatible endpoint<\/a>.<\/p>\n<p>For more information, refer to the <a href=\"https:\/\/developers.cloudflare.com\/workers-ai\/models\/gemma-4-26b-a4b-it\/\">Gemma 4 26B A4B model page<\/a>.<\/p>","protected":false},"excerpt":{"rendered":"<p>We are partnering with Google to bring @cf\/google\/gemma-4-26b-a4b-it to Workers AI. Gemma 4 26B A4B is a Mixture-of-Experts (MoE) model built from Gemini 3 research, with 26B total parameters and only 4B active per forward pass. By activating a small subset of parameters during inference, the model runs almost as fast as a 4B-parameter model [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-346","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/posts\/346","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/comments?post=346"}],"version-history":[{"count":0,"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/posts\/346\/revisions"}],"wp:attachment":[{"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/media?parent=346"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/categories?post=346"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.securinsight.ca\/index.php\/wp-json\/wp\/v2\/tags?post=346"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}