{"product_id":"ai-pyramid-computing-box-4gb-version-ax8850","title":"AI Pyramid Computing Box 4GB Version (AX8850)","description":"\u003cp\u003e\u003cvideo id=\"video\" playsinline=\"\" muted=\"\" controls=\"controls\" class=\"video-container\" width=\"100%\" style=\"border-radius: 8px; box-shadow: 0 4px 12px rgba(0,0,0,0.08);\"\u003e\n  \u003csource type=\"video\/mp4\" src=\"https:\/\/m5stack-doc.oss-cn-shenzhen.aliyuncs.com\/1216\/AI-003-Pro-AI-003-AI-Pyramid-video-EN.mp4\"\u003e\u003c\/video\u003e\u003c\/p\u003e\n\u003cstyle\u003e\n\/* ===== Scoped Description Style ===== *\/\n.product-description.rte {\n  font-family: -apple-system, BlinkMacSystemFont, \"Segoe UI\", Roboto, \"Helvetica Neue\", Arial, sans-serif;\n  color: #2c2c2c;\n  line-height: 1.65;\n  font-size: 16px;\n}\n\n\/* ===== Headings ===== *\/\n.product-description.rte h2 {\n  font-size: 1.8em;\n  color: #0D47A1;\n  border-left: 4px solid #1f6fe5;\n  padding-left: 12px;\n  margin-top: 32px;\n  margin-bottom: 16px;\n}\n\n\/* ===== H3 Titles Optimization ===== *\/\n.product-description.rte h3 {\n  font-size: 1.4em;\n  color: #0D47A1;\n  margin-top: 24px;\n  margin-bottom: 12px;\n  font-weight: 500;\n  padding-bottom: 6px;\n  border-bottom: 2px solid #e6e6e6;\n}\n\n\/* ===== Paragraphs ===== *\/\n.product-description.rte p {\n  margin-bottom: 20px;\n  line-height: 1.8;\n  color: #4a4f57;\n  font-size: 16px;\n}\n\n\/* ===== Paragraph Images (only in description) ===== *\/\n.product-description.rte img {\n  display: block;\n  max-width: 100%;\n  height: auto;\n  margin: 24px auto;\n  border-radius: 12px;\n  box-shadow: 0 8px 24px rgba(0, 0, 0, 0.06);\n}\n\n\/* ===== Lists ===== *\/\n.product-description.rte ul {\n  padding-left: 20px;\n  margin-bottom: 16px;\n  list-style-type: disc;\n}\n.product-description.rte li {\n  margin-bottom: 6px;\n}\n\n\/* ===== Links ===== *\/\n.product-description.rte a {\n  color: #0288D1;\n  text-decoration: none;\n  transition: color 0.3s ease;\n}\n.product-description.rte a:hover {\n  color: #01579B;\n}\n\n\/* ===== M5Stack-style Spec Table ===== *\/\n.product-description.rte .table-container {\n  width: 100%;\n  margin: 24px 0;\n  overflow-x: auto;\n}\n.product-description.rte .table-container table {\n  width: 100%;\n  border-collapse: collapse;\n  font-family: inherit;\n  font-size: 14px;\n  color: #2c2f36;\n  background-color: #ffffff;\n  border-radius: 10px;\n  overflow: hidden;\n  box-shadow: 0 4px 12px rgba(0, 0, 0, 0.04);\n}\n.product-description.rte .table-container thead th {\n  background: #1f6fe5;\n  color: #ffffff;\n  padding: 14px 16px;\n  text-align: center;\n  font-weight: 600;\n  border: none;\n  vertical-align: middle;\n}\n.product-description.rte .table-container td {\n  padding: 14px 16px;\n  border-bottom: 1px solid #e6ebf2;\n  vertical-align: middle;\n}\n.product-description.rte .table-container tbody td:first-child {\n  width: 36%;\n  text-align: center;\n  font-weight: 500;\n  color: #4a4f57;\n  background-color: rgba(31, 111, 229, 0.02);\n}\n.product-description.rte .table-container tbody tr:nth-child(even) {\n  background-color: #f7f9fc;\n}\n@media (hover: hover) {\n  .product-description.rte .table-container tbody tr:hover {\n    background-color: #eef3ff;\n  }\n}\n\n\/* ===== Learn \u0026 Documents Button ===== *\/\n.product-description.rte #learn-and-documents-btn {\n  display: inline-flex;\n  align-items: center;\n  padding: 6px 14px;\n  background-color: #1f6fe5;\n  color: #ffffff;\n  font-weight: 600;\n  border-radius: 6px;\n  margin-top: 8px;\n  text-decoration: none;\n  transition: background 0.3s ease;\n}\n.product-description.rte #learn-and-documents-btn:hover {\n  background-color: #1661c1;\n}\n\n\/* ===== Responsive Design for Smaller Screens (with table adjustments) ===== *\/\n@media screen and (max-width: 768px) {\n  .product-description.rte .table-container table,\n  .product-description.rte .table-container thead,\n  .product-description.rte .table-container tbody,\n  .product-description.rte .table-container th,\n  .product-description.rte .table-container td,\n  .product-description.rte .table-container tr {\n    display: block;\n    width: 100%;\n  }\n  .product-description.rte .table-container thead {\n    display: none;\n  }\n  .product-description.rte .table-container tbody tr {\n    padding: 12px 0;\n    border-bottom: 1px solid #e6ebf2;\n  }\n  .product-description.rte .table-container tbody td {\n    padding: 8px 16px;\n    border: none;\n    text-align: left;\n  }\n  .product-description.rte .table-container tbody td:first-child {\n    width: 100%;\n    background: none;\n    color: #1f6fe5;\n    font-weight: 600;\n    padding-top: 16px;\n  }\n  .product-description.rte .table-container tbody td:last-child {\n    padding-bottom: 16px;\n    color: #2c2f36;\n    line-height: 1.6;\n  }\n\n  \/* Ensure button appears correctly on mobile *\/\n  .product-description.rte #learn-and-documents-btn {\n    font-size: 14px;\n    padding: 8px 16px;\n  }\n}\n\u003c\/style\u003e\n\u003ch2 data-id=\"Description\" id=\"description\"\u003eDescription\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eAI Pyramid\u003c\/strong\u003e is a pyramid-shaped high-performance AI PC purpose-built for local AI inference and edge intelligence deployments. Powered by the Axera AX8850 SoC, it integrates an octa-core Cortex-A55 processor and a 24 TOPS @ INT8 NPU to effortlessly handle complex workloads including visual recognition, multimodal interaction, and on-device large model inference. AI Pyramid comes with 4GB LPDDR4x high-bandwidth memory paired with a dedicated hardware video processing engine, supporting 8K H.264\/H.265 encode\/decode and 16-channel 1080p parallel decoding to meet demands for AI vision analytics, video processing, and multi-stream media applications. Equipped with \u003cstrong\u003edual HDMI 2.0 digital multimedia output ports\u003c\/strong\u003e, dual Gigabit Ethernet, USB 3.0, and USB Type-C interfaces, it delivers exceptional flexibility for display output, networking, and peripheral expansion. It serves as a desktop-grade AI computing platform and is ideal for field deployment in edge computing scenarios. Designed for AI PCs, edge intelligent terminals, and smart interactive devices, AI Pyramid provides reliable AI inference performance for localized AI systems such as AI vision gateways, intelligent security, and local smart photo albums (Immich).\u003c\/p\u003e\n\u003cp\u003e\u003cimg style=\"width: 80%; height: auto;\" alt=\"AI Pyramid\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0056\/7689\/2250\/files\/DSC00525.webp?v=1774409868\u0026amp;width=700\"\u003e\u003c\/p\u003e\n\u003ch2 data-id=\"Features\" id=\"features\"\u003eFeatures\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eHigh Performance\n\u003cul\u003e\n\u003cli\u003eAxera AX8850 SoC\u003c\/li\u003e\n\u003cli\u003eCPU: Octa-core Cortex-A55 @ 1.7 GHz\u003c\/li\u003e\n\u003cli\u003eNPU: 24 TOPS @ INT8\u003c\/li\u003e\n\u003cli\u003e4GB (2+2) High-Bandwidth Memory: 64-bit LPDDR4x, 4266 Mbps\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eRich I\/O Interface Suite\n\u003cul\u003e\n\u003cli\u003e2× HDMI 2.0 digital audio\/video output ports, 4K@60fps supported\u003c\/li\u003e\n\u003cli\u003e4× USB-A 3.0 ports (1 internal onboard port)\u003c\/li\u003e\n\u003cli\u003e2× USB Type-C (USB Host + USB PD 3.0 100W power delivery)\u003c\/li\u003e\n\u003cli\u003e2× Gigabit Ethernet ports\u003c\/li\u003e\n\u003cli\u003e1× microSD card slot\u003c\/li\u003e\n\u003cli\u003e2× HY2.0-4P expansion interfaces\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eAudio Subsystem\n\u003cul\u003e\n\u003cli\u003eES8311 audio codec\u003c\/li\u003e\n\u003cli\u003eES7210 4-microphone array input\u003c\/li\u003e\n\u003cli\u003eAW8317A speaker amplifier\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eHardware Video Engine: 8K @ 30 fps H.264\/H.265 encoding \u0026amp; decoding, 16-channel 1080p parallel decoding supported\u003c\/li\u003e\n\u003cli\u003eSecure Boot \u0026amp; Encryption: AES\/DES\/3DES\/SHA-256 hardware security module\u003c\/li\u003e\n\u003cli\u003eNative AXCL Support: One-click deployment for CNN, Transformer, CLIP, Whisper, Llama 3.2, Qwen 3, InternVL3 and other models; H.264\/H.265 simultaneous encode\/decode\/transcode enabled\u003c\/li\u003e\n\u003cli\u003eOnboard STM32 Coprocessor for Extended Functions\n\u003cul\u003e\n\u003cli\u003ePower monitoring\u003c\/li\u003e\n\u003cli\u003eOLED status display\u003c\/li\u003e\n\u003cli\u003eUser control buttons\u003c\/li\u003e\n\u003cli\u003eRGB LED lighting\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 data-id=\"Package Contents\" id=\"package contents\"\u003ePackage Contents\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e1 × AI Pyramid\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 data-id=\"Applications\" id=\"applications\"\u003eApplications\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eAI PC \u0026amp; Edge Intelligent Terminals\u003c\/li\u003e\n\u003cli\u003eSmart Interactive Devices: Home Assistant, AIGC, voice cloning, meeting transcription\u003c\/li\u003e\n\u003cli\u003eAI Vision Gateways\u003c\/li\u003e\n\u003cli\u003eLocal AI Smart Photo Album (Immich)\u003c\/li\u003e\n\u003cli\u003eAI-Powered Intelligent Security (Frigate)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cimg style=\"width: 80%; height: auto;\" alt=\"AI Pyramid\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0056\/7689\/2250\/files\/6_bb4404d2-0ac0-45a8-a96a-f99c280dee31.webp?v=1774409888\u0026amp;width=700\"\u003e\u003c\/p\u003e\n\u003ch2 data-id=\"Specifications\" id=\"specifications\"\u003eSpecifications\u003c\/h2\u003e\n\u003cdiv class=\"table-container\"\u003e\n\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eSpecification\u003c\/th\u003e\n\u003cth\u003eParameter\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eSoC\u003c\/td\u003e\n\u003ctd\u003eAxera AX8850\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003eOcta-core Cortex-A55 @ 1.7 GHz\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNPU\u003c\/td\u003e\n\u003ctd\u003e24 TOPS @ INT8\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo Encoder\u003c\/td\u003e\n\u003ctd\u003e8K @ 30 fps H.264\/H.265 encoding, scaling \u0026amp; cropping supported\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo Decoder\u003c\/td\u003e\n\u003ctd\u003e8K @ 30 fps H.264\/H.265 decoding, 16-channel 1080p parallel decoding, scaling \u0026amp; cropping supported\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e4GB 64-bit LPDDR4x, 4266 Mbps (2+2)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003e32GB eMMC 5.1\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEthernet\u003c\/td\u003e\n\u003ctd\u003e2× Gigabit Ethernet ports\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB-A Ports\u003c\/td\u003e\n\u003ctd\u003e4× USB-A 3.0 (3× external + 1× internal onboard)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB Type-C Ports\u003c\/td\u003e\n\u003ctd\u003e2× USB Type-C (1× USB Host + 1× USB PD 3.0 100W, DC 9V\/12V\/20V compatible)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMultimedia Interface\u003c\/td\u003e\n\u003ctd\u003e2× HDMI 2.0 digital audio\/video output ports, 4K@60fps supported\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCooling\u003c\/td\u003e\n\u003ctd\u003eTurbo cooling fan with EC intelligent thermal control\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAudio Codec\u003c\/td\u003e\n\u003ctd\u003eES8311 audio codec\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMicrophone\u003c\/td\u003e\n\u003ctd\u003eES7210 microphone array input\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSpeaker\u003c\/td\u003e\n\u003ctd\u003eAW8317A amplifier, 4Ω 2W 2040 enclosed speaker\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRGB LED\u003c\/td\u003e\n\u003ctd\u003e48× RGB LEDs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSmartIO Status Display\u003c\/td\u003e\n\u003ctd\u003eOLED SSD1306 (32×128); supports IP address, system resource, custom text\/graphic display\u003cbr\u003ePanel dimensions: 28.54 × 8.58 × 1.22mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUser Buttons\u003c\/td\u003e\n\u003ctd\u003e2× user buttons (power on\/off + OLED page navigation)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Requirement\u003c\/td\u003e\n\u003ctd\u003ePD input rated ≥ DC 9V@3A (27W)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eProduct Weight\u003c\/td\u003e\n\u003ctd\u003e196.0g\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePackage Dimensions\u003c\/td\u003e\n\u003ctd\u003e144.5 × 105.0 × 62.0mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGross Weight\u003c\/td\u003e\n\u003ctd\u003e255.0g\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0056\/7689\/2250\/files\/1920x2260_5b28810b-e3e3-40fc-ac53-fe8f8096cc2b.webp?v=1774409952\u0026amp;width=700\" style=\"width: 80%; height: auto;\" alt=\"AI Pyramid\"\u003e\u003c\/p\u003e\n\u003cdiv style=\"background: #fff8e1; border: 1px solid #ffe0a3; border-left: 4px solid #f9a825; border-radius: 8px; padding: 14px 16px; margin: 24px 0;\"\u003e\n\u003cstrong style=\"display: block; color: #8d6e00; font-size: 13px; margin-bottom: 6px;\"\u003e Power Requirement \u003c\/strong\u003e \u003cspan style=\"color: #2c2c2c; font-size: 12.5px; line-height: 1.6;\"\u003e This device requires a PD adapter with a minimum output of DC 9V@3A (27W). The unit will not power on with a DC 5V supply. \u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv style=\"background: #fff8e1; border: 1px solid #ffe0a3; border-left: 4px solid #f9a825; border-radius: 8px; padding: 14px 16px; margin: 24px 0;\"\u003e\n\u003cstrong style=\"display: block; color: #8d6e00; font-size: 13px; margin-bottom: 6px;\"\u003e Memory Allocation \u003c\/strong\u003e \u003cspan style=\"color: #2c2c2c; font-size: 12.5px; line-height: 1.6;\"\u003e Memory partitioning between the AI Pyramid system and hardware acceleration resources is defined below:\u003cbr\u003e4GB variant (2GB + 2GB): 2GB allocated to system memory; 2GB reserved for hardware acceleration tasks including NPU compute and video encode\/decode.\u003cbr\u003eThis partitioning scheme ensures stable system operation while reserving dedicated memory for AI inference and multimedia processing. \u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv style=\"background: #fff8e1; border: 1px solid #ffe0a3; border-left: 4px solid #f9a825; border-radius: 8px; padding: 14px 16px; margin: 24px 0;\"\u003e\n\u003cstrong style=\"display: block; color: #8d6e00; font-size: 13px; margin-bottom: 6px;\"\u003e I2C Bus Notice \u003c\/strong\u003e \u003cspan style=\"color: #2c2c2c; font-size: 12.5px; line-height: 1.6;\"\u003e Avoid accessing the RTC chip during microphone recording, as this may cause unstable behavior on the SYS_I2C bus. \u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv style=\"background: #fff8e1; border: 1px solid #ffe0a3; border-left: 4px solid #f9a825; border-radius: 8px; padding: 14px 16px; margin: 24px 0;\"\u003e\n\u003cstrong style=\"display: block; color: #8d6e00; font-size: 13px; margin-bottom: 6px;\"\u003e RTC Clock Notice \u003c\/strong\u003e \u003cspan style=\"color: #2c2c2c; font-size: 12.5px; line-height: 1.6;\"\u003e After external power loss, the onboard RTC clock module retains timekeeping for up to approximately 20 hours. \u003c\/span\u003e\n\u003c\/div\u003e\n\u003ch2 data-id=\"Product Comparison\" id=\"product comparison\"\u003eProduct Comparison\u003c\/h2\u003e\n\u003cdiv class=\"compare-table-container\"\u003e\n\u003cdiv class=\"table-container\"\u003e\n\u003ctable\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth\u003eProduct Comparison\u003c\/th\u003e\n\u003cth\u003eAI Pyramid \u003cimg alt=\"AI Pyramid\" style=\"width: 40%; height: auto;\" src=\"https:\/\/m5stack-doc.oss-cn-shenzhen.aliyuncs.com\/1213\/AI-003_main_pictures_02.webp?width=700\"\u003e\n\u003c\/th\u003e\n\u003cth\u003eAI Pyramid-Pro \u003cimg alt=\"AI Pyramid-Pro\" style=\"width: 40%; height: auto;\" src=\"https:\/\/m5stack-doc.oss-cn-shenzhen.aliyuncs.com\/1216\/AI-003-Pro_main-pictures_02.webp?width=700\"\u003e\n\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eDRAM\u003c\/td\u003e\n\u003ctd\u003e4GB 64‑bit LPDDR4x, 4266 Mbps (2+2)\u003c\/td\u003e\n\u003ctd\u003e8GB 64‑bit LPDDR4x, 4266 Mbps (4+4)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eHD Digital Audio\/Video Interface\u003c\/td\u003e\n\u003ctd\u003e2x Output\u003c\/td\u003e\n\u003ctd\u003e1x Input + 1x Output\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEnclosure Color\u003c\/td\u003e\n\u003ctd\u003eTransparent\u003c\/td\u003e\n\u003ctd\u003eGray\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003ch2\u003eLearn and Documents\u003c\/h2\u003e\n → DOCUMENTS \n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"m5stack-store","offers":[{"title":"Default Title","offer_id":49566414569699,"sku":"see1787247218790","price":133.33,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0734\/2961\/4819\/files\/ai-pyramid-computing-box-4gb-version-ax8850_1.webp?v=1787247225","url":"https:\/\/regalcladfashion.shop\/products\/ai-pyramid-computing-box-4gb-version-ax8850","provider":"My Store","version":"1.0","type":"link"}