{"id":23063,"date":"2026-03-02T02:16:28","date_gmt":"2026-03-01T17:16:28","guid":{"rendered":"https:\/\/aireviewirush.com\/?p=23063"},"modified":"2026-03-02T02:16:28","modified_gmt":"2026-03-01T17:16:28","slug":"learn-how-to-run-excessive-efficiency-llms-domestically-on-the-arduino-uno-q","status":"publish","type":"post","link":"https:\/\/aireviewirush.com\/?p=23063","title":{"rendered":"Learn how to Run Excessive-Efficiency LLMs Domestically on the Arduino UNO Q"},"content":{"rendered":"<p> <br \/>\n<br \/><img decoding=\"async\" src=\"https:\/\/hackster.imgix.net\/uploads\/attachments\/1933206\/_ExO0KZ3nSo.blob?auto=compress%2Cformat&amp;w=400&amp;h=300&amp;fit=min\" alt=\"\"><\/p>\n<div>\n<p class=\"hckui__typography__bodyL\">Within the first few months for the reason that Arduino UNO Q was launched, individuals have fashioned many various opinions about it. Some love the improved computational horsepower and the power to run Linux, whereas others discover the App Lab atmosphere complicated and restrictive. No matter aspect of the fence you end up on, one factor is definite \u2014 it is vitally completely different from the Arduino boards that got here earlier than.<\/p>\n<p class=\"hckui__typography__bodyL\"><span>Together with the change has come quite a lot of uncertainty about what this board is de facto good for. With its STM32H5 coprocessor, it <\/span><em>can<\/em><span> do all of the issues an UNO is often used for. Nevertheless, given the additional price and complexity, you most likely wouldn\u2019t wish to use an UNO Q to blink some LEDs. If you&#8217;ll make investments on this new board, you&#8217;ll wish to use it for extra advanced tasks.<\/span><\/p>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_53 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\" role=\"button\"><label for=\"item-69e7b7564218a\" ><span class=\"\"><span style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input aria-label=\"Toggle\" aria-label=\"item-69e7b7564218a\"  type=\"checkbox\" id=\"item-69e7b7564218a\"><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/aireviewirush.com\/?p=23063\/#Extra_than_simply_blinking_LEDs\" title=\"Extra than simply blinking LEDs\">Extra than simply blinking LEDs<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/aireviewirush.com\/?p=23063\/#AI_on_the_edge\" title=\"AI on the edge\">AI on the edge<\/a><\/li><\/ul><\/nav><\/div>\n<h3 class=\"hckui__typography__h3 title-with-anchor\" id=\"toc-more-than-just-blinking-leds-0\"><span class=\"ez-toc-section\" id=\"Extra_than_simply_blinking_LEDs\"><\/span><a class=\"anchor\" href=\"#toc-more-than-just-blinking-leds-0\"><i class=\"fa fa-link\"\/><\/a><span>Extra than simply blinking LEDs<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"hckui__typography__bodyL\"><span>Alongside these strains, Edge Impulse&#8217;s Marc Pous has simply demonstrated a really fascinating means to make use of the UNO Q that might have been unthinkable earlier than the addition of the Dragonwing processor. He has written up a <\/span><a href=\"https:\/\/projecthub.arduino.cc\/marc-edgeimpulse\/running-local-llms-and-vlms-on-the-arduino-uno-q-with-yzma-74e288\" class=\"hckui__typography__linkBlue\" rel=\"nofollow noopener\" target=\"_blank\">temporary tutorial<\/a><span> explaining how one can run LLMs \u2014 and even VLMs \u2014 regionally on the board.<\/span><\/p>\n<p class=\"hckui__typography__bodyL\">The mission is constructed round yzma, a Go wrapper for llama.cpp created by Ron Evans, well-known for tasks like Gobot and TinyGo. yzma gives a clear interface that permits builders to combine high-performance inference into Go functions with out wrestling with CGo bindings. This gives a streamlined path to working trendy AI fashions instantly on the UNO Q\u2019s Debian-based Linux atmosphere.<\/p>\n<h3 class=\"hckui__typography__h3 title-with-anchor\" id=\"toc-ai-at-the-edge-1\"><span class=\"ez-toc-section\" id=\"AI_on_the_edge\"><\/span><a class=\"anchor\" href=\"#toc-ai-at-the-edge-1\"><i class=\"fa fa-link\"\/><\/a><span>AI on the edge<\/span><span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p class=\"hckui__typography__bodyL\">The tutorial walks customers via putting in Go on the board, establishing yzma, and pulling in appropriate GGUF fashions from Hugging Face. For text-only inference, Pous demonstrates the compact SmolLM2-135M-Instruct mannequin, which weighs in at roughly 135 million parameters. Due to quantization and the effectivity of llama.cpp, the mannequin can run regionally on the UNO Q\u2019s Arm-based system, enabling absolutely offline chat interactions.<\/p>\n<div>\n<div class=\"image_carousel__container__hGUHe undefined\">\n<p><span>This picture was used to check the VLM (\ud83d\udcf7: Marc Pous)<\/span><\/p>\n<\/div>\n<\/div>\n<p class=\"hckui__typography__bodyL\">Much more spectacular is the demonstration of a multimodal mannequin: SmolVLM2-500M-Video-Instruct. At round 500 million parameters, it&#8217;s small by trendy AI requirements however nonetheless able to processing photographs and quick video inputs alongside textual content prompts. In Pous\u2019 instance, the board analyzes a photograph of markers scattered throughout a desk and generates an in depth description \u2014 all with out sending knowledge to the cloud.<\/p>\n<p class=\"hckui__typography__bodyL\"><span>As an alternative of counting on distant APIs, builders can construct privacy-conscious edge programs that interpret photographs, reply to voice instructions, or analyze sensor knowledge regionally. For robotics and sensible house experiments specifically, the power to mix real-time microcontroller management with Linux-based AI inference opens up new design potentialities. In case you construct a few of your personal nice concepts with an UNO Q, remember to <\/span><a href=\"https:\/\/www.hackster.io\/projects\/new\" class=\"hckui__typography__linkBlue\" rel=\"nofollow noopener\" target=\"_blank\">tell us<\/a><span>.<\/span><\/p>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":"<p>Within the first few months for the reason that Arduino UNO Q was launched, individuals have fashioned many various opinions about it. Some love the improved computational horsepower and the power to run Linux, whereas others discover the App Lab atmosphere complicated and restrictive. No matter aspect of the fence you end up on, one [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":23065,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22],"tags":[],"class_list":{"0":"post-23063","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-iot"},"_links":{"self":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/23063","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=23063"}],"version-history":[{"count":1,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/23063\/revisions"}],"predecessor-version":[{"id":23064,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/posts\/23063\/revisions\/23064"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=\/wp\/v2\/media\/23065"}],"wp:attachment":[{"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=23063"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=23063"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aireviewirush.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=23063"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}