{"product_id":"lattepanda-mu-ultra-a-micro-x86-compute-module-for-on-device-ai-intel-core-ultra-5-226v-cpu-16gb-ram-97-tops-df-dfr1294","title":"LattePanda Mu Ultra - A Micro x86 Compute Module for On-device AI (Intel Core Ultra 5 226V CPU, 16GB RAM, 97 TOPS)","description":"\r\n\u003cp\u003eLattePanda Mu Ultra 226V is a micro x86 compute module built for on-device AI. Powered by an Intel Core Ultra 5 226V processor (Lunar Lake) with \u003cb\u003e16GB of LPDDR5X memory\u003c\/b\u003e running at \u003cb\u003e8533MT\/s\u003c\/b\u003e, it delivers \u003cb\u003eup to 97 TOPS\u003c\/b\u003e of combined AI performance across its CPU, GPU, and NPU—all on a credit-card-sized board. With rich expansion pins (PCIe 4.0, USB 3.2 Gen 2, HDMI\/DP outputs, etc.) and multi-OS support, it makes it suitable to integrate powerful local AI into robots, handhelds, and edge devices.\r\n\r\n\r\n\u003c\/p\u003e\u003cp\u003e\u003cb\u003e\u003cbr\u003e\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eMassive AI Power, Up to 97 TOPS for Local AI\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eThe LattePanda Mu Ultra 226V processor packs three compute engines into one module: an 8-core CPU, an Intel Arc GPU, and an Intel AI Boost NPU — delivering up to 97 TOPS of heterogeneous AI compute in total.  \r\n\u003c\/p\u003e\u003cp\u003eThe CPU, GPU, and NPU each handle the workloads they’re best suited for, enabling local execution of LLMs, VLMs, YOLO-based vision models, and speech models without a cloud connection, with no cloud connection required.\r\n\u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/Massive%20AI%20Power-226V.png\" alt=\"Massive AI Power - LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Massive AI Power - LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003ePowerful General Performance\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLattePanda Mu Ultra is also a seriously capable computer-on-module. The 8-core CPU and the Arc GPU enable logic control, accelerated graphics, and parallel computing with desktop-class performance. This allows the LattePanda Mu Ultra to handle dense workloads with responsive performance.\r\n\u003c\/p\u003e\r\n\u003cp\u003eAt a 37W TDP setting, the LattePanda Mu Ultra 226V achieved approximately 9,800 multi-core and 2,400 single-core points in Geekbench 6. Its Intel Arc 130V GPU scored approximately 2,900 in the 3DMark Time Spy Graphics test.\r\n\r\nIn OpenVINO NPU forward-pass testing, the module delivered 235.3 FPS with YOLO26n, 158.7 FPS with YOLO26s and 78.2 FPS with YOLO26m.\u003c\/p\u003e\r\n\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/3.Redefining%20on-device%20Benchmarks-4.png\" alt=\"Benchmark of LattePanda Mu Ultra Micro x86 AI Compute Module\" title=\"Benchmark of LattePanda Mu Ultra Micro x86 AI Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eLightning-Fast Unified Memory On Package\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLocal LLM performance relies heavily on memory bandwidth. The LattePanda Mu Ultra features a Memory-on-Package (MoP) with 16GB of LPDDR5X at 8533 MT\/s, delivering up to 136.5GB\/s of bandwidth for significantly faster token generation.\r\n\u003c\/p\u003e\u003cp\u003eIn addition, allocate up to 11.6GB as shared GPU memory to run larger models or support expanded context windows.\r\n\u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/LattePanda%20Mu%20Ultra%20Micro%20x86%20Compute%20Module%20(3).png\" alt=\"Lightning-Fast Unified Memory On Package of LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Lightning-Fast Unified Memory On Package of LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eCard-Sized, Fits Anywhere\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLattePanda Mu Ultra measures only 69.6mm x 60mm. The credit-card-sized form factor concentrates the processor, 16GB memory and expansion signals into a compact module suitable for space-constrained systems such as mobile robots, handheld instruments and smart terminals.\r\n\r\n\u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/LattePanda%20Mu%20Ultra%20Micro%20x86%20Compute%20Module%20(5).png\" alt=\"Card-Sized LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Card-Sized LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eActive or Idle, Efficient Power Consumption for Edge AI\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLattePanda Mu Ultra delivers more performance per watt than previous generations—so every token, frame, and inference consumes less energy. \r\n\u003c\/p\u003e\u003cp\u003eLow idle power consumption also suits local AI workloads, which often consist of short inference bursts followed by longer idle periods. Efficient power consumption under both active and idle conditions helps extend operating time in mains-powered and battery-powered applications.\r\n\u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/LattePanda%20Mu%20Ultra%20Micro%20x86%20Compute%20Module%20(4).png\" alt=\"Active or Idle - LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Active or Idle - LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eSupport for Popular AI Software Frameworks\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLattePanda Mu Ultra supports widely used AI software frameworks and runtimes. Intel OpenVINO enables acceleration across the CPU, GPU, and NPU, while runtimes and frameworks such as Ollama can run directly on the platform. Support for LLMs, VLMs, YOLO, and speech models helps simplify development and migration with familiar software tools.\r\n \u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/LattePanda%20Mu%20Ultra%20Micro%20x86%20Compute%20Module%20(6).png\" alt=\"Multi AI Software Frameworks and OS Support - LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Multi AI Software Frameworks and OS Support - LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eMulti OS Support\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eThe LattePanda Mu Ultra x86 AI compute module supports multiple operating systems, including Windows 11 and Ubuntu 24.04 or later, providing options for different development and deployment requirements.\r\n\r\n\r\n\u003c\/p\u003e\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eFlexible Expansion Pins\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLattePanda Mu Ultra provides extensive pin access, including flexible PCIe 4.0 configurations with up to 4 x1, 4 x2, or 2 x4 links, two USB 3.2 Gen 2 ports, six USB 2.0 ports, three HDMI\/DP outputs, and additional expansion signals. This flexibility supports the development of application-specific hardware configurations.\r\n \u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/LattePanda%20Mu%20Ultra%20Micro%20x86%20Compute%20Module%20(7).png\" alt=\"Flexible Expansion Pins - LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Flexible Expansion Pins - LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cb\u003eReady-to-Use Carrier Board for Faster Development\u003c\/b\u003e\u003c\/p\u003e\r\n\u003cp\u003e\r\n  As a compute module, LattePanda Mu Ultra requires a compatible carrier board to provide power input, storage expansion and physical peripheral connectors.\r\n\u003c\/p\u003e\u003cp\u003eThe \u003ca href=\"https:\/\/www.dfrobot.com\/product-3155.html\" target=\"_blank\"\u003eMini Carrier Board\u003c\/a\u003e offers a compact development platform with two full-featured USB Type-C ports, two USB 3.2 Gen 2 Type-A ports, 2.5G Ethernet, HDMI 2.0, OCuLink and separate M.2 slots for NVMe SSD and WLAN expansion.\r\n\u003c\/p\u003e\r\n\u003cp\u003eThe \u003ca href=\"https:\/\/www.dfrobot.com\/product-2822.html\" target=\"_blank\"\u003eLite Carrier Board\u003c\/a\u003e also supports LattePanda Mu Ultra, with limitations on some ports. \u003ca href=\"https:\/\/docs.lattepanda.com\/content\/mu_edition\/lite_carrier\/#compatibility-list\" target=\"_blank\"\u003eSee the compatibility list\u003c\/a\u003e for details before selecting interfaces for a Mu Ultra configuration.\r\n\u003c\/p\u003e\r\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\r\n\u003cp\u003e\u003cb\u003eOpen-Source Carrier Board Reference Files\u003c\/b\u003e\u003c\/p\u003e\r\n\u003cp\u003e\r\n  LattePanda provides \u003ca href=\"https:\/\/github.com\/LattePandaTeam\/LattePanda-Mu\/tree\/main\/Electricals\/Examples\" target=\"_blank\"\u003eopen-source carrier board reference files\u003c\/a\u003e for adapting carrier board designs to application-specific interface, layout and form-factor requirements. These reference materials help reduce the work required to begin a custom carrier board design.\r\n\u003c\/p\u003e\r\n\r\n\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/10.Carrier%20Boards.png\" alt=\"Ready-to-use Carrier Boards of LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Ready-to-use Carrier Boards of LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\u003cp\u003e\u003cb\u003eCustomized Solutions\r\n\u003c\/b\u003e\u003c\/p\u003e\u003cp\u003eLattePanda offers customization services for carrier boards, boot screens, BIOS functions, operating systems, and related requirements. Specific customization requests can be sent to solution@lattepanda.com.\u003c\/p\u003e\r\n\u003cp\u003eLattePanda provides technical support for the evaluation and implementation of customized solutions.\r\n\r\n \u003c\/p\u003e\u003cp style=\"text-align: center; \"\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1294\/customzied%20solutions.jpg\" alt=\"Customized Solutions - LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Customized Solutions - LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cb\u003e\u003cfont color=\"#ff0000\"\u003eNote: \u003c\/font\u003e\u003c\/b\u003eThe LattePanda Mu Ultra series includes onboard memory but no onboard storage. A compatible SSD, which is not included, must be installed through the carrier board’s M.2 slot before use.\r\n\u003c\/p\u003e\r\n\u003ch2\u003eFeatures:\u003c\/h2\u003e\r\n\u003cli\u003eIntel Core Ultra 5 Processor 226V (8-core, 8-thread, up to 4.5GHz)\r\n\u003c\/li\u003e\u003cli\u003eUp to 97 TOPS of combined AI performance: Intel Arc 130V GPU (7 Xe-cores, up to 53 TOPS Int8) ; Intel AI Boost NPU (up to 40 TOPS Int8)\r\n\u003c\/li\u003e\u003cli\u003eOnboard 16GB LPDDR5X 8533MT\/s unified Memory-on-Package (MoP), with up to 11.6GB allocatable as GPU shared memory\r\n\u003c\/li\u003e\u003cli\u003eCredit-card-sized: 69.6mm x 60mm\r\n\u003c\/li\u003e\u003cli\u003eMultiple OS support: Windows 11, Ubuntu 24.04 or later\r\n\u003c\/li\u003e\u003cli\u003eRich expansion pins, including: flexible PCIe 4.0 (up to 4 x1, 4 x2, or 2 x4), 2 USB 3.2 Gen2, 6 USB 2.0, 3 HDMI\/DP, 1 eDP, 3 UART, 3 I2C, 14 GPIOs, 1 CNVio3\r\n\u003c\/li\u003e\u003ch2\u003eApplications:\u003c\/h2\u003e\r\n\u003cli\u003eSmart Al Terminals\u003c\/li\u003e\r\n\u003cli\u003ePortable Instruments\u003c\/li\u003e\r\n\u003cli\u003eAutonomous Mobile Robots\u003c\/li\u003e\r\n\u003cli\u003eService Robots\u003c\/li\u003e\r\n\u003cli\u003eEdge Al Vision\u003c\/li\u003e\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1295-1\/9.Application.png\" alt=\"Application of LattePanda Mu Ultra Micro x86 Compute Module\" title=\"Application of LattePanda Mu Ultra Micro x86 Compute Module\"\u003e\r\n\u003c\/p\u003e \r\n\u003ch2\u003eSpecification:\u003c\/h2\u003e\r\n\u003cli\u003eProcessor: Intel Core Ultra 5 Processor 226V\r\n\u003c\/li\u003e\u003cli\u003eGPU: Intel Arc 130V GPU\r\n\u003c\/li\u003e\u003cli\u003eNPU: Intel AI Boost\r\n\u003c\/li\u003e\u003cli\u003eMemory: 16GB LPDDR5X 8533MT\/s\r\n\u003c\/li\u003e\u003cli\u003eStorage: No onboard storage, external SSD is required (via the M.2 slot on a carrier board)\r\n\u003c\/li\u003e\u003cli\u003eDisplay: 3 HDMI\/DP + 1 eDP; supports up to 3 independent displays simultaneously\u003c\/li\u003e\r\n\u003cli\u003ePower: DC 9~20V\r\n\u003c\/li\u003e\u003cli\u003eOperating System: Windows 11, Ubuntu 24.04 or later\r\n\u003c\/li\u003e\u003cli\u003eEnvironment: 0~60°C; 0~80% relative humidity\r\n\u003c\/li\u003e\u003cli\u003eSize: 69.6mm x 60mm\r\n\u003c\/li\u003e\r\n\u003cbr\u003e\r\n\u003cp\u003eI\/O\r\n\u003c\/p\u003e\u003cli\u003ePCIe 4.0: up to 4 x1, 4 x2, or 2 x4 links\r\n\u003c\/li\u003e\u003cli\u003eUSB 3.2 Gen2 (10Gbps): 2 ports\r\n\u003c\/li\u003e\u003cli\u003eUSB 2.0 (480Mbps): 6 ports\r\n\u003c\/li\u003e\u003cli\u003eCNVio3: 1 port\r\n\u003c\/li\u003e\u003cli\u003e3 I2C, 3 UART, 14 GPIO\u003c\/li\u003e\r\n\u003cp\u003e\u003c\/p\u003e\r\n\r\n\u003ch2\u003eProduct Includes:\u003c\/h2\u003e\r\n\u003cli\u003eLattePanda Mu Ultra Compute Module (226V, 16GB) x1\r\n\u003c\/li\u003e\u003cli\u003eProduct Manual x1\u003c\/li\u003e\r\n","brand":"DFRobot","offers":[{"title":"Default Title","offer_id":42904516198482,"sku":"DF-DFR1294","price":1629.0,"currency_code":"NZD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0735\/0383\/files\/DFR1294_Main_01.jpg?v=1794828985","url":"https:\/\/www.pakronics.co.nz\/products\/lattepanda-mu-ultra-a-micro-x86-compute-module-for-on-device-ai-intel-core-ultra-5-226v-cpu-16gb-ram-97-tops-df-dfr1294","provider":"Pakronics®","version":"1.0","type":"link"}