{"id":683488,"date":"2026-06-04T07:53:10","date_gmt":"2026-06-04T07:53:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/683488\/"},"modified":"2026-06-04T07:53:10","modified_gmt":"2026-06-04T07:53:10","slug":"google-ai-edge-gallery-launches-to-macos","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/683488\/","title":{"rendered":"Google AI Edge Gallery launches to macOS"},"content":{"rendered":"<p>\t<img width=\"1600\" height=\"800\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/06\/google-ai-edge-gallery.jpg\" class=\"skip-lazy wp-post-image\" alt=\"\"  decoding=\"async\" fetchpriority=\"high\"\/><\/p>\n<p class=\"wp-block-paragraph\">In addition to Google AI Edge Gallery, which lets users run Gemma models locally on their Macs, the company also released the Gemma 4 12B model and the Google AI Edge Eloquent dictation app for the Mac. Here are the details.<\/p>\n<p>A bit of background<\/p>\n<p class=\"wp-block-paragraph\">The majority of users who rely on LLMs for everyday tasks tend to use ChatGPT, Claude, or Gemini, which are cloud-based models running on OpenAI, Anthropic, and Google\u2019s servers.<\/p>\n<p class=\"wp-block-paragraph\">Another way to interact with LLMs is through local models. These are usually much smaller and less capable than the trillion-parameter models that run in the cloud, but they also come with several advantages.<\/p>\n<p class=\"wp-block-paragraph\">For one, being less capable than cloud-based models does not mean they are bad. Also, they do not require an active internet connection, since they run on the computer\u2019s own processing power. Additionally, the better the computer, the faster the responses, and the larger the models it can handle. And finally, because everything runs locally, these models are more private too, since conversation data does not need to leave the device.<\/p>\n<p class=\"wp-block-paragraph\">There are a few ways to install local models on a Mac, and <a href=\"https:\/\/9to5mac.com\/2025\/08\/06\/how-to-run-gpt-oss-20b-on-mac\/\" rel=\"nofollow noopener\" target=\"_blank\">we covered this here<\/a>, when OpenAI released its own open models. But in a nutshell, you need to install platforms such as <a href=\"https:\/\/ollama.com\" rel=\"nofollow noopener\" target=\"_blank\">Ollama<\/a> and <a href=\"https:\/\/lmstudio.ai\" rel=\"nofollow noopener\" target=\"_blank\">LM Studio<\/a>, and then install a model that can runs smoothly on your Mac\u2019s hardware.<\/p>\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/huggingface.co\" rel=\"nofollow noopener\" target=\"_blank\">Hugging Face<\/a> hosts thousands of open models to choose from, including those from frontier labs. However, platforms such as Ollama and LM Studio also offer ways to install these models directly from them.<\/p>\n<p class=\"wp-block-paragraph\">Which brings us to <a href=\"https:\/\/developers.google.com\/edge\/gallery\" rel=\"nofollow noopener\" target=\"_blank\">Google AI Edge Gallery<\/a>, Google\u2019s platform for running AI models locally. Google already offered a Google AI Edge Gallery app for Android and for iOS, but today the company released it for macOS as well.<\/p>\n<p>Google AI Edge Gallery and Gemma 4 12B<\/p>\n<p class=\"wp-block-paragraph\">One thing to note right from the get-go is that, contrary to Ollama and LM Studio, which allow users to install any AI model compatible with their hardware, Google AI Edge Gallery for Mac currently only offers access to 5 of Google\u2019s own models, where \u2018it\u2019 stands for instruct, meaning they can be tuned to follow user instructions rather than simply complete text:<\/p>\n<p>Gemma-4-12B-it<\/p>\n<p>Gemma-4-E2B-it<\/p>\n<p>Gemma-4-E4B-it<\/p>\n<p>Gemma-3n-E2B-it<\/p>\n<p>Gemma-3n-E4B-it<\/p>\n<p class=\"wp-block-paragraph\">The top item on the list is particularly notable. <a href=\"https:\/\/blog.google\/innovation-and-ai\/technology\/developers-tools\/introducing-gemma-4-12B\/\" rel=\"nofollow noopener\" target=\"_blank\">Gemma 4 12B<\/a> was released today, and it was designed to bring agentic, multimodal intelligence directly to your laptop,\u201d according to Google.<\/p>\n<p class=\"wp-block-paragraph\">While most consumer-facing local models from frontier AI labs tend to stay somewhere between 2 billion and 9 billion parameters, Google says Gemma 4\u2019s 12-billion-parameter design delivers performance comparable to its 26-billion-parameter mixture-of-experts model, while still being \u201csmall enough to run locally on consumer laptops with 16GB of RAM.\u201d<\/p>\n<p class=\"wp-block-paragraph\">Gemma 4 12B is also multimodal, which means it can handle text, vision, and audio. Google says that the model also packs good coding capabilities, \u201callowing you to extract meaningful insights from your data right on your device.\u201d<\/p>\n<p class=\"wp-block-paragraph\">You can learn more about Google AI Edge Gallery <a href=\"https:\/\/developers.googleblog.com\/bringing-gemma-4-12b-to-your-laptop-unlocking-local-agentic-workflows-with-google-ai-edge\/\" rel=\"nofollow noopener\" target=\"_blank\">here<\/a>, and you can learn more about Gemma 4 12B <a href=\"https:\/\/blog.google\/innovation-and-ai\/technology\/developers-tools\/introducing-gemma-4-12B\/\" rel=\"nofollow noopener\" target=\"_blank\">here<\/a>.<\/p>\n<p>Google AI Edge Eloquent<\/p>\n<p class=\"wp-block-paragraph\">Alongside Gemma 12B and the release of Google AI Edge Gallery for macOS, Google also launched the <a href=\"https:\/\/developers.google.com\/edge\/eloquent\" rel=\"nofollow noopener\" target=\"_blank\">Google AI Edge Eloquent<\/a> app for Mac today, after bringing the app to iOS a few months ago.<\/p>\n<p class=\"wp-block-paragraph\">Google AI Edge Eloquent is a free dictation app that captures what users say and transcribes it while polishing the text, removing disfluencies, and making light edits for clarity and flow. Processing is done on-device, rather than on the cloud.<\/p>\n<p class=\"wp-block-paragraph\">The app also lets users choose between different writing styles and add custom words, such as names, jargon, and other terms they use often. That helps avoid the kind of frequent miscorrections that dictation apps can otherwise make with specific words and phrases.<\/p>\n<p class=\"wp-block-paragraph\">You can learn more about Google AI Edge eloquent <a href=\"https:\/\/developers.google.com\/edge\/eloquent\" rel=\"nofollow noopener\" target=\"_blank\">here<\/a>.<\/p>\n<p>Worth checking out on Amazon<\/p>\n<p>\t\t<a target=\"_blank\" rel=\"nofollow noopener\" href=\"https:\/\/google.com\/preferences\/source?q=https:\/\/9to5mac.com\" aria-label=\"Add 9to5Mac as a preferred source on Google\"><br \/>\n\t\t\t<img decoding=\"async\" class=\"google-preferred-source-badge-dark\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/05\/google-preferred-source-badge-dark.png\" alt=\"Add 9to5Mac as a preferred source on Google\"\/><br \/>\n\t\t\t<img decoding=\"async\" class=\"google-preferred-source-badge-light\" src=\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/05\/google-preferred-source-badge-light.png\" alt=\"Add 9to5Mac as a preferred source on Google\"\/><br \/>\n\t\t<\/a><\/p>\n<p class=\"disclaimer-affiliate\">FTC: We use income earning auto affiliate links. <a href=\"https:\/\/9to5mac.com\/about\/#affiliate\" rel=\"nofollow noopener\" target=\"_blank\">More.<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"In addition to Google AI Edge Gallery, which lets users run Gemma models locally on their Macs, the&hellip;\n","protected":false},"author":2,"featured_media":683489,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[31],"tags":[74],"class_list":["post-683488","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/683488","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=683488"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/683488\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/683489"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=683488"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=683488"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=683488"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}