{"product_id":"lattepanda-sigma-2-the-embeddable-ai-single-board-server-intel-core-ultra-x7-358h-64gb-ram-1tb-ssd-180-tops-pre-order-df-dfr1316","title":"LattePanda Sigma 2 - The Embeddable AI Single Board Server (Intel Core Ultra X7 358H, 64GB RAM, 1TB SSD, 180 TOPS) (Pre-Order)","description":"\u003cp\u003eLattePanda Sigma 2 is an embeddable AI single board server built for local AI workloads. Powered by the Intel Core Ultra X7 358H processor (Panther Lake) with 64GB of LPDDR5X memory, it delivers up to 180 TOPS of total AI performance across its CPU, GPU and NPU—enough to run 35B-class quantized MoE models and AI agents entirely on-device. With dual Thunderbolt 4 ports, dual 10Gb Ethernet ports, four M.2 slots, OCuLink, and rich I\/O on a 3.5-inch board, it brings scalable AI power to local AI appliances, homelabs, and robots.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e\u003cbr\u003e\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eFlagship AI Performance on a Single Board \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThe Intel Core Ultra X7 358H brings a 16-core CPU, an Intel Arc B390 GPU with 12 Xe-cores, and an Intel NPU together on one board. These compute engines deliver up to 180 TOPS of combined peak INT8 AI performance: 122 TOPS from the GPU, 50 TOPS from the NPU, and 8 TOPS from the CPU.\u003c\/p\u003e\n\u003cp\u003eFrom local model inference to application processing and graphics, this architecture provides the computing foundation for AI servers and embedded systems.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(3).jpg\" alt=\"LattePanda Sigma 2 - Flagship AI Performance on a Single Board\" title=\"LattePanda Sigma 2 - Flagship AI Performance on a Single Board\"\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eExpand Local AI Compute\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eExtend beyond onboard compute with compatible M.2 AI accelerators and external GPUs. M.2 M-Key, OCuLink, and Thunderbolt 4 provide multiple expansion paths as local AI projects grow.\u003c\/p\u003e\n\u003cp\u003eAdditional compute devices provide resources for more models and agent services, supporting deployments that bring multiple local AI workloads together on one platform.\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(1).jpg\" alt=\"LattePanda Sigma 2 - Flagship AI Performance on a Single Board\" title=\"LattePanda Sigma 2 - Flagship AI Performance on a Single Board\"\u003e \u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(2).jpg\" alt=\"LattePanda Sigma 2 - Flagship AI Performance on a Single Board\" title=\"LattePanda Sigma 2 - Flagship AI Performance on a Single Board\"\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eUnprecedented Leap in Local Compute\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eRun 35B-class quantized MoE models directly on the board and bring model inference closer to local applications and data. The local LLM benchmarks show both input-processing and text-generation speeds, providing a practical view of model performance.\u003c\/p\u003e\n\u003cp\u003eGeneral computing takes a substantial step forward as well. The 16-core CPU and Intel Arc B390 GPU deliver higher CPU and graphics benchmark scores than the previous-generation LattePanda Sigma, supporting demanding applications alongside local AI workloads.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(4).jpg\" alt=\"LattePanda Sigma 2 - Unprecedented Leap in Local Compute\" title=\"LattePanda Sigma 2 - Unprecedented Leap in Local Compute\"\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eAmple Unified Memory for Local AI Inference\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eLattePanda Sigma 2 features 64GB of dual-channel LPDDR5X-8533 memory with 136.5GB\/s of theoretical bandwidth. Large capacity provides room for model weights and runtime data, while high bandwidth supports the data-intensive demands of local inference.\u003c\/p\u003e\n\u003cp\u003eUp to 59GB of this unified memory can be allocated for GPU use, providing space for 35B-class quantized MoE models and the KV cache used to retain conversation context. The result is a platform built for local agents working with longer conversations and substantial inputs.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(5).jpg\" alt=\"Lightning-Fast Unified Memory for Local AI Agents\" title=\"Lightning-Fast Unified Memory for Local AI Agents\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eCompact by Design, Ready to Embed\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eLocal AI compute, high-speed networking, and extensive I\/O fit within a 3.5-inch board measuring 146 × 102mm. The compact footprint supports integration into local AI appliances, mobile robots, and instruments where internal space matters.\u003c\/p\u003e\n\u003cp\u003eCompute and hardware connectivity stay together on one board, creating a compact foundation for embedded AI systems.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(7).jpg\" alt=\"LattePanda Sigma 2 - Compact by Design. Ready to Embed.\" title=\"LattePanda Sigma 2 - Compact by Design. Ready to Embed.\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eFast Under Load, Efficient at Idle\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eLattePanda Sigma 2 delivers nearly twice the text-generation speed of the previous-generation Sigma in the illustrated local AI test, while average DC input power increases from 35W to 38W.\u003c\/p\u003e\n\u003cp\u003eAt idle, average DC input power drops to 4.5W, compared with 5W for the previous generation. Higher efficiency during inference and lower idle power make it a practical foundation for local AI services that remain available around the clock.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(6).jpg\" alt=\"LattePanda Sigma 2 - Fast Under Load, Efficient at Idle\" title=\"LattePanda Sigma 2 - Fast Under Load, Efficient at Idle\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eWindows \u0026amp; Ubuntu Support\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eLattePanda Sigma 2 supports Windows 11 and Ubuntu 24.04 LTS or later, providing operating-system options for application development and deployment.\u003c\/p\u003e\n\u003cp\u003eThe included SSD comes with Ubuntu pre-installed, providing a starting point for local AI projects.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eSupport for Popular AI Software Frameworks \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eBuild local AI applications with Intel OpenVINO, Ollama, and llama.cpp. OpenVINO provides acceleration options across the CPU, GPU, and NPU, while Ollama and llama.cpp offer additional workflows for local model deployment.\u003c\/p\u003e\n\u003cp\u003eFrom language and vision-language models to YOLO object detection and speech processing, the platform supports a broad range of AI development tasks through compatible software tools.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(11).jpg\" alt=\"LattePanda Sigma 2 - Support for Popular AI Software Frameworks\" title=\"LattePanda Sigma 2 - Support for Popular AI Software Frameworks\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eLocal AI, Ready Out of the Box\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThe included 1TB NVMe SSD comes pre-installed with Ubuntu, GPU and NPU drivers, OpenVINO Model Server (OVMS), OpenClaw, and local AI models. Drivers, inference software, and models are already in place, reducing the setup work required to begin local AI development.\u003c\/p\u003e\n\u003cp\u003eStart the local inference API to provide on-device model inference for OpenClaw and other compatible agents. The local endpoint also provides a foundation for custom applications, with no cloud inference API required.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(12).jpg\" alt=\"LattePanda Sigma 2 - Local AI, Ready Out of the Box\" title=\"LattePanda Sigma 2 - Local AI, Ready Out of the Box\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eComplete I\/O, All on One Board\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eDual Thunderbolt 4 ports, dual 10Gb Ethernet, USB 3.2 Gen 2, HDMI 2.1, eDP, serial interfaces, and GPIO connect local AI compute to networks, displays, peripherals, and physical hardware.\u003c\/p\u003e\n\u003cp\u003eThree high-power M.2 M-Key slots accommodate NVMe SSDs and compatible AI accelerators, alongside an M.2 E-Key slot for additional expansion. OCuLink and Thunderbolt 4 provide connection options for external GPU docks, bringing storage, networking, and compute expansion together on one board.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(9).jpg\" alt=\"LattePanda Sigma 2 - Complete I\/O. All on One Board\" title=\"LattePanda Sigma 2 - Complete I\/O. All on One Board\"\u003e \u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/LattePanda%20Sigma%202%20Features%20(7).jpg\" alt=\"LattePanda Sigma 2 - Expand Local AI Compute\" title=\"LattePanda Sigma 2 - Expand Local AI Compute\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eOne Board for AI and Hardware Control\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThe onboard RP2350 microcontroller brings programmable hardware control alongside Intel-powered AI computing. While the Intel processor handles model inference and application logic, the RP2350 handles sensor inputs and actuator-control tasks.\u003c\/p\u003e\n\u003cp\u003ePreloaded MicroPython firmware provides a starting point for programming hardware interfaces, including I2C, SPI, UART, and analog inputs through GPIO. Together, the two processors form a foundation for robotics, interactive devices, and sensor-connected AI systems.\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(10).jpg\" alt=\"LattePanda Sigma 2 - From Local AI to Real-World Action\" title=\"LattePanda Sigma 2 - From Local AI to Real-World Action\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eProfessional Technical Support and Integration Help\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThe LattePanda team provides technical support for installation, configuration, troubleshooting, and system integration, helping projects move from initial setup toward deployment.\u003c\/p\u003e\n\u003cp\u003eTechnical enquiries: \u003ca href=\"http:\/\/techsupport@lattepanda.com\" target=\"_blank\"\u003etechsupport@lattepanda.com\u003c\/a\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eCustomization for Project Requirements \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eLattePanda Sigma 2 offers customization options for system integration, including port removal, custom boot screens, BIOS feature adjustments, and tailored operating systems.\u003c\/p\u003e\n\u003cp\u003eCustomization enquiries: \u003ca href=\"http:\/\/solution@lattepanda.com\" target=\"_blank\"\u003esolution@lattepanda.com\u003c\/a\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(14).jpg\" alt=\"LattePanda Sigma 2 - Customization for Project Requirements\" title=\"LattePanda Sigma 2 - Customization for Project Requirements\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003ciframe src=\"https:\/\/www.youtube.com\/embed\/iMAlLteQPYU\" width=\"1440\" height=\"810\" class=\"note-video-clip\"\u003e\u003c\/iframe\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eVideo: LattePanda Sigma 2 - The Embeddable AI Single Board Server\u003c\/p\u003e\n\u003ch2\u003eFeatures:\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eIntel Core Ultra X7 358H processor with 16 cores, 16 threads, and a maximum frequency of 4.8GHz.\u003c\/li\u003e\n\u003cli\u003eUp to 180 TOPS of combined peak INT8 AI performance across the CPU, GPU, and NPU.\u003c\/li\u003e\n\u003cli\u003eIntel Arc B390 GPU with 12 Xe-cores and up to 122 TOPS of peak INT8 AI performance.\u003c\/li\u003e\n\u003cli\u003e64GB dual-channel LPDDR5X-8533 unified memory, with up to 59GB allocatable for GPU use.\u003c\/li\u003e\n\u003cli\u003eIncluded 1TB NVMe SSD with Ubuntu and a pre-installed local AI software environment.\u003c\/li\u003e\n\u003cli\u003eDual Thunderbolt 4, dual 10Gb Ethernet, three high-power M.2 M-Key slots, one M.2 E-Key slot, and OCuLink.\u003c\/li\u003e\n\u003cli\u003eOnboard RP2350 microcontroller with preloaded MicroPython firmware for sensor interfaces and hardware control.\u003c\/li\u003e\n\u003cli\u003eCompact 3.5-inch board format measuring 146 × 102mm.\u003c\/li\u003e\n\u003cli\u003eSupport for Windows 11 and Ubuntu 24.04 LTS or later.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eApplications:\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eLocal AI model and agent servers\u003c\/li\u003e\n\u003cli\u003eEmbedded AI appliances\u003c\/li\u003e\n\u003cli\u003eHomelab servers and development systems\u003c\/li\u003e\n\u003cli\u003eRobotics and sensor-connected AI projects\u003c\/li\u003e\n\u003cli\u003eInteractive devices with AI-driven hardware control\u003c\/li\u003e\n\u003cli\u003eCompact instruments with local AI processing\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/dfimg.dfrobot.com\/enshop\/image\/data\/DFR1316\/lp%20sigma%202%20features%20pic%20(13).jpg\" alt=\"Applications of LattePanda Sigma 2 - The Embeddable AI Single Board Server (Intel Core Ultra X7 358H, 64GB RAM, 1TB SSD)\" title=\"Applications of LattePanda Sigma 2 - The Embeddable AI Single Board Server (Intel Core Ultra X7 358H, 64GB RAM, 1TB SSD)\"\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003ch2\u003eSpecification:\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eProcessor: Intel Core Ultra X7 358H; 16 cores, 16 threads, up to 4.8GHz\u003c\/li\u003e\n\u003cli\u003eGPU: Intel Arc B390; 12 Xe-cores, up to 2.5GHz\u003c\/li\u003e\n\u003cli\u003eNPU: Intel NPU\u003c\/li\u003e\n\u003cli\u003eCo-processor: RP2350 MCU\u003c\/li\u003e\n\u003cli\u003eMemory: 64GB dual-channel LPDDR5X-8533\u003c\/li\u003e\n\u003cli\u003eStorage: 1TB M.2 NVMe SSD\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003eDisplay\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e1 × HDMI 2.1\u003c\/li\u003e\n\u003cli\u003e1 × eDP 1.5, 4-lane\u003c\/li\u003e\n\u003cli\u003eDisplayPort 2.1 via USB-C (Thunderbolt 4)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003eExpansion and Connectivity\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e2 × Thunderbolt 4, 40Gbps\u003c\/li\u003e\n\u003cli\u003e1 × OCuLink, PCIe 4.0 ×2\u003c\/li\u003e\n\u003cli\u003e2 × USB 3.2 Gen 2 Type-A, 10Gbps\u003c\/li\u003e\n\u003cli\u003e2 × USB 2.0 Type-A, 480Mbps\u003c\/li\u003e\n\u003cli\u003e1 × USB 2.0 header\u003c\/li\u003e\n\u003cli\u003e2 × 10Gb Ethernet, RJ45\u003c\/li\u003e\n\u003cli\u003e1 × 3.5mm microphone\/headphone combo jack\u003c\/li\u003e\n\u003cli\u003e1 × RS-232\/485 header\u003c\/li\u003e\n\u003cli\u003e1 × GPIO header\u003c\/li\u003e\n\u003cli\u003e1 × front panel header\u003c\/li\u003e\n\u003cli\u003e1 × front audio header\u003c\/li\u003e\n\u003cli\u003e3 × M.2 M-Key: PCIe 5.0 ×2 \/ PCIe 4.0 ×4 \/ PCIe 4.0 ×1\u003c\/li\u003e\n\u003cli\u003e1 × M.2 E-Key: PCIe 4.0 ×1, USB 2.0, CNVio\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003ePower\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eDC input: 15–20V\u003c\/li\u003e\n\u003cli\u003eUSB-C PD input: 20V\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003eOperating System Support\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eWindows 11\u003c\/li\u003e\n\u003cli\u003eUbuntu 24.04 LTS or later\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003eOperating Environment\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eOperating temperature: 0–40°C\u003c\/li\u003e\n\u003cli\u003eRelative humidity: 0–80%\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003cp\u003eDimensions\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eBoard format: 3.5-inch\u003c\/li\u003e\n\u003cli\u003eSize: 146 × 102mm\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eProduct Includes:\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eLattePanda Sigma 2 Single Board Server (358H, 64GB) x1\u003c\/li\u003e\n\u003cli\u003eActive Cooling Fan (Assembled) x1\u003c\/li\u003e\n\u003cli\u003eM.2 NVMe SSD WD SN7100 1TB (Assembled, Pre-installed Ubuntu OS) x1\u003c\/li\u003e\n\u003cli\u003eMetal Protective Bottom Plate x1\u003c\/li\u003e\n\u003cli\u003eThermal Pads for M.2 SSD x3\u003c\/li\u003e\n\u003cli\u003ePower Adapter with DC cable x1\u003c\/li\u003e\n\u003cli\u003eAC Cable(EU \u0026amp; US \u0026amp; UK) for power adapter x3\u003c\/li\u003e\n\u003cli\u003eRTC Battery(Assembled) x 1\u003c\/li\u003e\n\u003cli\u003eUser Manual x 1\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"DFRobot","offers":[{"title":"Default Title","offer_id":42904516624466,"sku":"DF-DFR1316","price":7597.0,"currency_code":"NZD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0735\/0383\/files\/DFR1316_Main_01.jpg?v=1794829038","url":"https:\/\/www.pakronics.co.nz\/products\/lattepanda-sigma-2-the-embeddable-ai-single-board-server-intel-core-ultra-x7-358h-64gb-ram-1tb-ssd-180-tops-pre-order-df-dfr1316","provider":"Pakronics®","version":"1.0","type":"link"}