{"id":412889,"date":"2026-01-16T10:05:10","date_gmt":"2026-01-16T10:05:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/ca\/412889\/"},"modified":"2026-01-16T10:05:10","modified_gmt":"2026-01-16T10:05:10","slug":"raspberry-pis-new-add-on-board-has-8gb-of-ram-for-running-gen-ai-models","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ca\/412889\/","title":{"rendered":"Raspberry Pi\u2019s new add-on board has 8GB of RAM for running gen AI models"},"content":{"rendered":"<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1ymtmqpi _17nnmdy1 _17nnmdy0 _1xwtict1\">Raspberry Pi is launching a new add-on board capable of running generative AI models locally on the Raspberry Pi 5. <a href=\"https:\/\/www.raspberrypi.com\/news\/introducing-the-raspberry-pi-ai-hat-plus-2-generative-ai-on-raspberry-pi-5\/\" rel=\"nofollow noopener\" target=\"_blank\">Announced on Thursday<\/a>, the <a href=\"https:\/\/www.raspberrypi.com\/products\/ai-hat-plus-2\/\" rel=\"nofollow noopener\" target=\"_blank\">$130 AI HAT+ 2<\/a> is an upgraded \u2014 and more expensive \u2014 version of the module <a href=\"https:\/\/www.raspberrypi.com\/products\/ai-hat\/\" rel=\"nofollow noopener\" target=\"_blank\">launched last year<\/a>, now offering 8GB of RAM and a Hailo 10H chip with 40 TOPS of AI performance.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1ymtmqpi _17nnmdy1 _17nnmdy0 _1xwtict1\">Once connected, the Raspberry Pi 5 will use the AI HAT+ 2 to handle AI-related workloads while leaving the main board\u2019s Arm CPU available to complete other tasks. Unlike the previous AI HAT+, which is focused on image-based AI processing, the AI HAT+ 2 comes with onboard RAM and can run small gen AI models like Llama 3.2 and DeepSeek-R1-Distill, along with a series of Qwen models. You can train and fine-tune AI models using the device as well.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1ymtmqpi _17nnmdy1 _17nnmdy0 _1xwtict1\">A <a href=\"https:\/\/www.youtube.com\/watch?v=9tvWtIRxDck\" rel=\"nofollow noopener\" target=\"_blank\">demo shared by Raspberry Pi<\/a> shows how you can use the add-on board to power an AI model capable of generating a text-based description of a camera stream, as well as answer a question about whether there are any people in the scene. Another shows how you <a href=\"https:\/\/www.youtube.com\/watch?v=KA1uVpvcQJc&amp;embeds_referring_euri=https%3A%2F%2Fwww.raspberrypi.com%2F&amp;source_ve_path=MjM4NTE\" rel=\"nofollow noopener\" target=\"_blank\">can translate text<\/a> from French to English with Qwen2.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1ymtmqpi _17nnmdy1 _17nnmdy0 _1xwtict1\">However, tech YouTuber <a href=\"https:\/\/www.jeffgeerling.com\/blog\/2026\/raspberry-pi-ai-hat-2\/\" rel=\"nofollow noopener\" target=\"_blank\">Jeff Geerling found<\/a> that a standalone Raspberry Pi 5 with 8GB of RAM generally outperformed the AI HAT+ 2 across the supported models. Geerling links the lower performance to power draw, as the Pi 5 can operate at up to 10 watts, while the AI HAT+ 2 is limited to 3W.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1ymtmqpi _17nnmdy1 _17nnmdy0 _1xwtict1\">Though the AI HAT+ 2 may be ideal for specific use cases, Geerling notes that the add-on board\u2019s extra 8GB of RAM is \u201cnot quite enough to give this HAT an advantage over just paying for the bigger 16GB Pi with more RAM, which will be more flexible and run models faster.\u201d The AI HAT+ released last year, can also handle AI image processing for a cheaper $70 starting price.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1ymtmqpi _17nnmdy1 _17nnmdy0 _1xwtict1\">Raspberry Pi says more and \u201clarger\u201d AI models \u201care being readied for updates, and should be available to install soon after launch.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"Raspberry Pi is launching a new add-on board capable of running generative AI models locally on the Raspberry&hellip;\n","protected":false},"author":2,"featured_media":412890,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[62,276,277,49,48,195,44,64,61],"class_list":{"0":"post-412889","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-ca","12":"tag-canada","13":"tag-gadgets","14":"tag-news","15":"tag-tech","16":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/412889","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=412889"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/412889\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/412890"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=412889"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=412889"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=412889"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}