{"product_id":"nvidia-jetson-agx-thor-developer-kit-for-ai-robotics-edge-computing","title":"NVIDIA Jetson AGX Thor Developer Kit for AI Robotics \u0026 Edge Computing","description":"\u003cdiv\u003e\n\u003ch1\u003eNVIDIA Jetson AGX Thor Developer Kit for AI Robotics \u0026amp; Edge Computing\u003c\/h1\u003e\n\u003cp\u003eThe \u003cstrong\u003eNVIDIA Jetson AGX Thor Developer Kit\u003c\/strong\u003e is the ultimate edge AI platform for next-generation humanoid robotics and physical AI applications. Powered by the cutting-edge \u003cstrong\u003eBlackwell GPU architecture\u003c\/strong\u003e and featuring \u003cstrong\u003e128GB of LPDDR5X memory\u003c\/strong\u003e, this developer kit delivers an astounding \u003cstrong\u003e2070 FP4 TFLOPS of AI compute performance\u003c\/strong\u003e within a compact \u003cstrong\u003e130W power envelope\u003c\/strong\u003e. Compared to the Jetson AGX Orin, the Thor offers up to \u003cstrong\u003e7.5 times more AI performance\u003c\/strong\u003e and \u003cstrong\u003e3.5 times better energy efficiency\u003c\/strong\u003e, making it the definitive platform for running the latest generative AI models, vision-language-action (VLA) models, and large language models at the edge.\u003c\/p\u003e\n\n\u003ch2\u003eWhy Developers Choose Jetson AGX Thor\u003c\/h2\u003e\n\u003cp\u003eBuilt from the ground up for physical AI and robotics, the Jetson AGX Thor is designed to accelerate low-latency, real-time applications with advanced \u003cstrong\u003eBlackwell Multi-Instance GPU (MIG) technology\u003c\/strong\u003e and a robust \u003cstrong\u003e14-core Arm Neoverse-V3AE CPU\u003c\/strong\u003e. Whether you're building autonomous machines, intelligent robots, or edge AI systems for manufacturing, logistics, healthcare, or smart cities, the Thor delivers the performance, flexibility, and sensor fusion capabilities you need to innovate faster.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eUnmatched AI Performance\u003c\/strong\u003e: 2070 FP4 TFLOPS to effortlessly run generative AI models including Isaac GR00T N, LLMs, and VLMs\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMassive Memory Bandwidth\u003c\/strong\u003e: 128GB LPDDR5X memory for handling large transformer models and real-time multi-sensor data\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-Speed Connectivity\u003c\/strong\u003e: QSFP slot with 4 × 25GbE networking, multi-GbE RJ45, USB 3.2 Gen 2 Type-A and Type-C ports, HDMI 2.0b, and DisplayPort 1.4a\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAdvanced Accelerators\u003c\/strong\u003e: Third-generation Programmable Vision Accelerator (PVA), dual NVDEC\/NVENC engines for video encoding and decoding, and optical flow accelerator\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eReady-to-Deploy Software Stack\u003c\/strong\u003e: Ships with JetPack 7, Ubuntu 24.04 LTS, and native support for NVIDIA Isaac robotics, Metropolis visual AI, and Holoscan sensor processing\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eComplete Out-of-the-Box Experience\u003c\/strong\u003e: Includes 1TB NVMe SSD preloaded with software, Wi-Fi 6E module, and 140W power supply\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eExceptional Performance for Physical AI\u003c\/h2\u003e\n\u003cp\u003eThe Jetson AGX Thor is architected specifically for humanoid robots and advanced autonomous systems. The \u003cstrong\u003eBlackwell GPU\u003c\/strong\u003e introduces FP4 precision, roughly doubling throughput over INT8 for models that support it, enabling real-time multimodal perception, decision-making, and control. The \u003cstrong\u003e14-core Arm Neoverse-V3AE CPU\u003c\/strong\u003e ensures ultra-low latency for safety-critical applications, while the suite of accelerators handles demanding vision tasks, video encoding\/decoding (up to 4 × 8Kp30 or 10 × 4Kp60), and sensor fusion at scale.\u003c\/p\u003e\n\n\u003ch2\u003eExtensive Connectivity for Multi-Sensor Fusion\u003c\/h2\u003e\n\u003cp\u003eFor high-speed sensor integration and real-time data processing, the developer kit offers extensive I\/O options perfectly suited for robotics and autonomous systems:\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003e1 × QSFP slot\u003c\/strong\u003e with 4 × 25GbE for high-bandwidth networking\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e1 × Multi-GbE RJ45\u003c\/strong\u003e connector (5GbE capable)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e2 × USB 3.2 Gen 2 Type-A\u003c\/strong\u003e ports\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e2 × USB 3.2 Gen 2 Type-C\u003c\/strong\u003e ports (one can be used for power delivery)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e1 × HDMI 2.0b\u003c\/strong\u003e output\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e1 × DisplayPort 1.4a\u003c\/strong\u003e output\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e16 × CSI-2 camera lanes\u003c\/strong\u003e for multi-camera robotics applications\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePCIe Gen 5 support\u003c\/strong\u003e for high-speed storage and expansion\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWi-Fi 6E module\u003c\/strong\u003e included\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCAN, RS-232\u003c\/strong\u003e, and additional debug interfaces\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eSoftware Stack Designed for Edge AI\u003c\/h2\u003e\n\u003cp\u003eThe Jetson AGX Thor runs a seamless cloud-to-edge AI software ecosystem designed specifically for physical AI applications. \u003cstrong\u003eJetPack 7 SDK\u003c\/strong\u003e ships preloaded on a 1TB NVMe SSD with \u003cstrong\u003eUbuntu 24.04 LTS\u003c\/strong\u003e, reducing setup time and source-compilation work. The kit supports:\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA Isaac\u003c\/strong\u003e for robotics and Isaac GR00T N foundational models for humanoid robots\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA Metropolis\u003c\/strong\u003e for visual agentic AI and video analytics\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA Holoscan\u003c\/strong\u003e for sensor processing and real-time data pipelines\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA agentic AI workflows\u003c\/strong\u003e like Video Search and Summarization (VSS)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCUDA 13.0\u003c\/strong\u003e, TensorRT, and Docker containerized workflows for rapid prototyping\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eIdeal Applications\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eHumanoid robotics and general-purpose robotic platforms\u003c\/li\u003e\n\u003cli\u003eAutonomous vehicles and mobile machines with multi-sensor fusion\u003c\/li\u003e\n\u003cli\u003eSmart city infrastructure and visual agentic AI systems\u003c\/li\u003e\n\u003cli\u003eManufacturing automation and industrial robotics\u003c\/li\u003e\n\u003cli\u003eHealthcare and medical robotics\u003c\/li\u003e\n\u003cli\u003eRetail analytics and edge AI vision systems\u003c\/li\u003e\n\u003cli\u003eResearch and development for frontier robotics and generative AI\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eWhat's in the Box\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eNVIDIA Jetson AGX Thor Developer Kit with Jetson T5000 module pre-installed on reference carrier board\u003c\/li\u003e\n\u003cli\u003e140W power supply with international adapters\u003c\/li\u003e\n\u003cli\u003eWi-Fi 6E wireless module (installed)\u003c\/li\u003e\n\u003cli\u003e1TB NVMe SSD with JetPack 7 and Ubuntu 24.04 LTS preloaded\u003c\/li\u003e\n\u003cli\u003eQuick start guide\u003c\/li\u003e\n\u003cli\u003eAntenna accessories (may vary by retailer)\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eFull Specifications\u003c\/h2\u003e\n\n\u003ch3\u003eCompute\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Architecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell GPU\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI Performance\u003c\/td\u003e\n\u003ctd\u003e2070 FP4 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003e14-core Arm Neoverse-V3AE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e128GB LPDDR5X\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eModule\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Jetson T5000 system-on-module (SoM)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMulti-Instance GPU (MIG)\u003c\/td\u003e\n\u003ctd\u003eSupported (Blackwell MIG technology)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eVideo \u0026amp; Vision\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo Decode\u003c\/td\u003e\n\u003ctd\u003eDual NVDEC; up to 4 × 8Kp30 or 10 × 4Kp60 (H.265, H.264, AV1, VP9, VP8, MPEG-2\/-4)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVideo Encode\u003c\/td\u003e\n\u003ctd\u003eDual NVENC; up to 6 × 4Kp60 (H.265, H.264)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVision Accelerator\u003c\/td\u003e\n\u003ctd\u003e3rd-generation Programmable Vision Accelerator (PVA 3.0)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOptical Flow Accelerator\u003c\/td\u003e\n\u003ctd\u003eIncluded\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCamera Support\u003c\/td\u003e\n\u003ctd\u003e16 × CSI-2 camera lanes\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eDisplay\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Outputs\u003c\/td\u003e\n\u003ctd\u003e1 × HDMI 2.0b, 1 × DisplayPort 1.4a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMaximum Resolution\u003c\/td\u003e\n\u003ctd\u003eUp to 8K (7680 × 4320) @ 30Hz\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMulti-Display Support\u003c\/td\u003e\n\u003ctd\u003eUp to 4 independent displays\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eConnectivity \u0026amp; I\/O\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eNetworking\u003c\/td\u003e\n\u003ctd\u003e1 × QSFP slot (4 × 25GbE), 1 × RJ45 Multi-GbE (5GbE capable)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB Ports\u003c\/td\u003e\n\u003ctd\u003e2 × USB 3.2 Gen 2 Type-A, 2 × USB 3.2 Gen 2 Type-C (one supports power delivery)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWireless\u003c\/td\u003e\n\u003ctd\u003eWi-Fi 6E module included, Bluetooth\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003e1TB NVMe SSD (preloaded with software), PCIe Gen 5 support\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAdditional Interfaces\u003c\/td\u003e\n\u003ctd\u003eCAN, RS-232, JTAG debug connector (2 × 5-pin header), USB Type-C debug port\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003ePower \u0026amp; Environment\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Consumption\u003c\/td\u003e\n\u003ctd\u003eConfigurable 40W - 130W (typical 130W for developer kit)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Supply\u003c\/td\u003e\n\u003ctd\u003e140W AC adapter (included)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCooling\u003c\/td\u003e\n\u003ctd\u003eHeatsink with active fan (included)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003ePhysical Specifications\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eModule Form Factor\u003c\/td\u003e\n\u003ctd\u003eApprox. 87 × 100mm with 699-pin B2B connector\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDeveloper Kit Weight\u003c\/td\u003e\n\u003ctd\u003eApproximately 1.94kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMagnetic Cover\u003c\/td\u003e\n\u003ctd\u003eIncluded for carrier board access\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eSoftware\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating System\u003c\/td\u003e\n\u003ctd\u003eUbuntu 24.04 LTS (preloaded)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSDK\u003c\/td\u003e\n\u003ctd\u003eJetPack 7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI Frameworks\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Isaac (including Isaac GR00T N), Metropolis, Holoscan, CUDA 13.0, TensorRT\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eContainer Support\u003c\/td\u003e\n\u003ctd\u003eDocker (primary), additional runtime configuration available\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eModel Support\u003c\/td\u003e\n\u003ctd\u003eVision Language Action (VLA) models, Large Language Models (LLMs), Vision Language Models (VLMs), generative AI models\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003cp\u003e\u003cem\u003eSpecifications are sourced from the manufacturer product page and may be updated.\u003c\/em\u003e\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Nvidia","offers":[{"title":"Default Title","offer_id":44324919640142,"sku":"PA-NVIDIAJETSONAGXTH","price":8690.0,"currency_code":"AUD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0676\/3134\/9838\/files\/Jetson_AGX_Thor_Devkit__white_1024_20x_20576.jpg?v=1789260541","url":"https:\/\/projectorsaustralia.com.au\/products\/nvidia-jetson-agx-thor-developer-kit-for-ai-robotics-edge-computing","provider":"Projectors Australia","version":"1.0","type":"link"}