{"title":"NVIDIA Jetson","description":"\u003cp\u003eAs a solution provider of open source solutions, the Firefly team has developed a series of products that carry NVIDIA Jetson Nano series SoM modules based on years of development experience. They are:\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003ca href=\"https:\/\/www.firefly.store\/collections\/ai-servers\"\u003e\u003cstrong\u003eAI Server\u003c\/strong\u003e\u003c\/a\u003e (up to 10 computing nodes can be configured; supports the Ollama local large model deployment framework and the private deployment of modern mainstream AI models; configures the aBMC intelligent management system; supports mainstream network models and custom operator development; supports Docker containerization and rapid deployment of algorithm applications).\u003c\/li\u003e\n\u003cli\u003e\n\u003ca href=\"https:\/\/www.firefly.store\/collections\/edge-computing\"\u003e\u003cstrong\u003eEdge Computing Mini PC\u003c\/strong\u003e\u003c\/a\u003e (supports all current AI models, implements larger and more complex deep neural networks, realizes object recognition, target detection and tracking, speech recognition, and other visual development functions, and meets the needs of more artificial intelligence application scenarios).\u003c\/li\u003e\n\u003cli\u003e\n\u003ca href=\"https:\/\/www.firefly.store\/collections\/ai-box\"\u003e\u003cstrong\u003eAIBOX Series Embedded PC\u003c\/strong\u003e\u003c\/a\u003e (it is widely used in scenarios such as intelligent monitoring, AI teaching, computing services, edge computing, private deployment of large language models, data security and privacy protection, etc).\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003eThe \u003cstrong\u003eNVIDIA Jetson Orin developer kit\u003c\/strong\u003e series system on module is a high-performance edge computing platform based on the Ampere architecture. The computing power is 6-8 times higher than that of the NVIDIA Jetson Xavier series. Jetson Orin continues the modular concept of the NVIDIA Jetson series and emphasizes hardware compatibility and rapid deployment. It adopts the standard Jetson carrier board design and supports fast connecting peripherals such as cameras, sensors, and network modules.\u003c\/p\u003e","products":[{"product_id":"aibox-orinnano-67tops-ai-big-model-of-edge-computing-jetson-module-nvidia","title":"AIBOX-OrinNano Jetson Orin Nano Embedded PC","description":"\u003cp\u003eAIBOX-OrinNano is equipped with NVIDIA's original Jetson Orin Nano core module (8GB RAM version), providing up to 67 TOPS of computing power, supporting private deployment of mainstream AI models such as Transformer and ROS robot models, thereby realizing larger and more complex deep neural networks, and realizing visual development tasks such as object recognition, target detection and tracking, and speech recognition, meeting higher-level AI application scenario requirements.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-OrinNano_AIBOX-OrinNX_Specification_EN.pdf?v=1749620262\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-Orin-Nano\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplication Cases \u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/technical-case\/aibox-application-case-background-removal-via-u-net\"\u003e\u003cstrong\u003eBackground Removal via U²-Net\u003c\/strong\u003e\u003c\/a\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/news\/monocular-depth-estimation-aibox-application\"\u003eMonocular Depth Estimation\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-performance Edge Computing Module: \u003c\/strong\u003eThe NVIDIA Jetson Orin Nano edge computing module (8GB version) is equipped with a six-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (including 32 Tensor Cores), which can run multiple AI application pipelines simultaneously and provide powerful inference performance.\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMultiple Deep Learning Frameworks: \u003c\/strong\u003eIt supports a variety of cuDNN-accelerated deep learning frameworks, including PaddlePaddle, PyTorch, TensorFlow, MATLAB, MxNet, Caffe2, Chainer, Keras, etc., as well as custom operator development, and supports Docker containerization technology.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAluminum Alloy Enclosure With Efficient Heat Dissipation: \u003c\/strong\u003eAIBOX adopts an industrial-grade all-metal shell and an aluminum alloy structure with good thermal conductivity. The grille design on the side of the top cover is conducive to external airflow and efficient heat dissipation, ensuring computing performance and stability even in high-temperature operating environments.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplication\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack And Ecosystem:\u003c\/strong\u003e NVIDIA JetPack, Isaac ROS, and reference AI workflows seamlessly integrate cutting-edge technologies into your products without expensive in-house AI resources. Experience end-to-end acceleration of AI applications and get to market faster using the same powerful technology that drives data center and cloud deployments.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eThe Private Deployment Of Large Models:\u003c\/strong\u003e Large language model: supports the Ollamalocal large model deployment framework and private deployment of ultra-large-scale parameterized models: Llama3, Phi-3 Mini. Vision model: supports EfficientVIT, NanoOWL, NanoSAM, SAM, TAM. AI painting: supports ComfyUIgraphical deployment framework and private deployment of Flux, and a stable Diffusion image generation model in the AIGC field.\u003cbr\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ORINAIBOX.webp?v=1751269631\"\u003e\u003c\/strong\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"8G RAM+128G SSD \/ Standard without Wifi","offer_id":51090462539916,"sku":null,"price":479.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+128G SSD \/ Deepseek Deployed without Wifi","offer_id":51090462572684,"sku":null,"price":499.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD \/ Standard without Wifi","offer_id":51090462605452,"sku":null,"price":599.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM+256G SSD \/ Deepseek Deployed without Wifi","offer_id":51090462638220,"sku":null,"price":619.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/800800-1_03c4016b-006a-45e0-9ae7-4875f2eb8425.jpg?v=1782727377"},{"product_id":"aibox-orinnx-157tops-ai-big-model-of-edge-computing-jetson-module-nvidia","title":"AIBOX-OrinNX Jetson Orin NX Embedded PC","description":"\u003cp\u003eWith up to 157 TOPS of computing power, AIBOX-OrinNX can run almost all modern AI models, including Transformer and ROS robot models. Implement larger and more complex deep neural networks, such as using TensorFlow, OpenCV, JetPack, MXNet, PyTorch, etc., to achieve object recognition, target detection and tracking, speech recognition, and other visual development functions, and adapt to a variety of AI application scenarios.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIBOX-OrinNano_AIBOX-OrinNX_Specification_EN.pdf?v=1749620262\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/AIBOX-Orin-NX\/index.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplication Cases\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/technical-case\/aibox-application-case-background-removal-via-u-net\"\u003e\u003cstrong\u003eBackground Removal via U²-Net\u003c\/strong\u003e\u003c\/a\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003e\u003ca href=\"https:\/\/www.firefly.store\/blogs\/news\/monocular-depth-estimation-aibox-application\"\u003eMonocular Depth Estimation\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-performance Edge Computing Jetson Orin NX Module: \u003c\/strong\u003eThe NVIDIA Jetson Orin NX edge computing module (16GB version) is equipped with an eight-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (including 32 Tensor Cores), which can run multiple AI application pipelines simultaneously and provide powerful inference performance.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 157 TOPS of Computing Power: \u003c\/strong\u003eThe AIBOX-OrinNX provides up to 157 TOPS of computing power and is equipped with a 128GB PCIe NVMe SSD. The Ubuntu 22.04-based JETSON system provides a comprehensive desktop Linux environment with accelerated graphics capabilities and support for libraries such as NVIDIA CUDA, TensorRT, and CuDNN.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupport 18-channel 1080p@30fps H.265 Video Decoding: \u003c\/strong\u003eAIBOX-OrinNX supports up to 1×8K30 (H.265), 2×4K60 (H.265), 4×4K30 (H.265), 9×1080p60 (H.265), and 18×1080p30 (H.265) video decoding to meet the needs of diverse AI application scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAluminum Alloy Enclosure With Efficient Heat Dissipation: \u003c\/strong\u003eThe embedded Mini PC adopts an industrial-grade full metal shell and aluminum alloy structure with excellent thermal conductivity. The grille design on the top cover effectively conducts heat and ensures computing performance and stability even under high-temperature operating conditions. The small and exquisite device operates stably and meets the requirements of various industrial-grade applications.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack and Ecosystem: \u003c\/strong\u003eEnable edge AI and robotics development with the world’s most comprehensive AI software stack and ecosystem, powered by generative AI at the edge and the NVIDIA Metropolis and Isaac platforms. NVIDIA JetPack, Isaac ROS, and reference AI workflows seamlessly integrate cutting-edge technologies into your products without the need for expensive in-house AI resources. Experience end-to-end acceleration of AI applications and get to market faster using the same powerful technology that drives data center and cloud deployments.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eGenerative AI at The Edge: \u003c\/strong\u003eNVIDIA Jetson Orin provides unparalleled AI computing power, large unified memory, and a comprehensive software stack with excellent energy efficiency to drive the latest generative AI applications. It can quickly infer any Transformer-based generative AI model and provide excellent edge performance on MLPerf.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eThe Private Deployment of Large Models: \u003c\/strong\u003eLarge language models; Vision models; AI painting; Traditional network architectures; Deep learning frameworks; Docker containerization.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ORINAIBOX.webp?v=1751269631\"\u003e\u003c\/strong\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"16G RAM+128G SSD \/ Standard without Wifi","offer_id":51090462670988,"sku":null,"price":1089.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+128G SSD \/ Deepseek Deployed without Wifi","offer_id":51090462703756,"sku":null,"price":1109.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G SSD \/ Standard without Wifi","offer_id":51090462736524,"sku":null,"price":1199.0,"currency_code":"USD","in_stock":false},{"title":"16G RAM+256G SSD \/ Deepseek Deployed without Wifi","offer_id":51090462769292,"sku":null,"price":1209.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/800800-1.jpg?v=1782727380"},{"product_id":"ec-orinnx-157tops-computing-power-ai-edge-computing-host-jetson-module-nvidia-nvidia","title":"EC-OrinNX Jetson Orin NX Edge AI Fanless PC","description":"\u003cp style=\"text-align: left;\"\u003eEC-OrinNX is equipped with the NVIDIA Jetson Orin NX core module (16GB RAM version), providing up to 157 TOPS of computing power. It can run all current AI models and support larger and more complex deep neural networks. It has visual development functions such as object recognition, target detection and tracking, and speech recognition to meet the needs of a wider range of artificial intelligence application scenarios.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/EC-OrinNano_EC-OrinNX_Specification_EN.pdf?v=1749540358\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/EC-Orin-NX\/preface.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 18px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-performance Edge Computing Module:\u003c\/strong\u003e The NVIDIA Jetson Orin NX edge computing module (16GB version) uses an eight-core ARM CPU and a 1024-core NVIDIA Ampere architecture.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 157 TOPS of Computing Power: \u003c\/strong\u003eEC-OrinNX provides up to 157 TOPS of computing power and can run all current AI models, including Transformer and ROS models. It supports building larger and more complex deep neural networks using frameworks such as TensorFlow, OpenCV, JetPack, MXNet, and PyTorch. The computer has object recognition, target detection and tracking, speech recognition, and other visual development capabilities, and is suitable for a wide range of AI application scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eThe Private Deployment of Large Models: \u003c\/strong\u003eLarge language models, Vision models, AI painting, Traditional network architectures, Deep learning frameworks, Docker containerization.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eGenerative AI at The Edge: \u003c\/strong\u003eNVIDIA Jetson Orin provides unparalleled AI computing power, large unified memory, and a comprehensive software stack with excellent energy efficiency to drive the latest generative AI applications. It can quickly infer any Transformer-based generative AI model and provide excellent edge performance on MLPerf.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack and Ecosystem: \u003c\/strong\u003eEmpower edge AI and robotics development with the world’s most comprehensive AI software stack and ecosystem. Powered by edge-generated AI and the Nvidia Metropolis and Isaac platforms, NVIDIA JetPack, Isaac ROS, and reference AI workflows, the software stack and ecosystem seamlessly integrate edge-generated AI technologies into your products without the need for expensive in-house AI resources. Experience end-to-end acceleration of AI applications and accelerate time to market using the same powerful technology that drives data center and cloud deployments.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupport 18-channel 1080p30 H.265 Video Decoding: \u003c\/strong\u003eEC-OrinNX supports video decoding of up to 1×8K30 (H.265), 2×4K60 (H.265), 4×4K30 (H.265), 9×1080p60 (H.265), and 18×1080p30 (H.265), meeting the diverse needs of AI application scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAluminum Alloy Housing: \u003c\/strong\u003eThe device adopts industrial-grade aluminum alloy housing and has efficient fanless passive heat dissipation function, ensuring stable operation around the clock and meeting various industrial application requirements. Its space-saving design supports wall-mounting and can be flexibly installed on walls or industrial automation equipment.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 18px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eRobotics\u003c\/li\u003e\n\u003cli\u003eEdge Computing\u003c\/li\u003e\n\u003cli\u003eLarge Models\u003c\/li\u003e\n\u003cli\u003eSmart Industry\u003c\/li\u003e\n\u003cli\u003eSmart Healthcare\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ec-orin_inter.webp?v=1750058577\"\u003e\u003c\/strong\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"16G RAM +128G SSD With wifi","offer_id":51090962743436,"sku":null,"price":1149.0,"currency_code":"USD","in_stock":false},{"title":"16G RAM +128G SSD Without wifi","offer_id":51090962776204,"sku":null,"price":1119.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM Without Wifi And SSD","offer_id":51090962808972,"sku":null,"price":1089.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM +128G SSD With wifi","offer_id":51090962841740,"sku":null,"price":819.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM +128G SSD Without wifi","offer_id":51090962874508,"sku":null,"price":789.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM Without Wifi And SSD","offer_id":51090962907276,"sku":null,"price":749.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/EC-OrinNX_-800800-2_e506d917-f7c1-49e2-8582-b812f7ae6e23.jpg?v=1782727693"},{"product_id":"ec-orinnano-67tops-computing-power-ai-edge-computing-host-jetson-module-nvidia-nvidia","title":"EC-OrinNano Jetson Orin Nano Edge AI Fanless PC","description":"\u003cp\u003eEC-OrinNano is equipped with the NVIDIA Jetson Orin Nano core module, which provides up to 67 TOPS of computing power. It can realize the private deployment of current mainstream AI models, support larger and more complex deep neural networks, and has visual development functions such as object recognition, target detection and tracking, and speech recognition to meet the needs of a wider range of artificial intelligence application scenarios.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/EC-OrinNano_EC-OrinNX_Specification_EN.pdf?v=1749540358\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/EC-Orin-Nano\/preface.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cdiv style=\"position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden; background: #000;\"\u003e\u003cvideo poster=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/9_5.jpg?v=1760148022\" style=\"position: absolute; top: 0; left: 0; width: 100%; height: 100%;\" playsinline=\"\" controls=\"controls\"\u003e\n    \u003csource src=\"https:\/\/cdn.shopify.com\/videos\/c\/o\/v\/88cbe6c335ad49d394e6de705916f145.mp4\"\u003e\u003c\/video\u003e\u003c\/div\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003e67 TOPS Edge Computing Power: \u003c\/strong\u003eWith a computing power of up to 67 TOPS, it can run all current AI models, including Transformer and ROS models. It supports building larger and more complex deep neural networks using frameworks such as TensorFlow, OpenCV, JetPack, MXNet, and PyTorch. The computer has object recognition, target detection and tracking, speech recognition, and other visual development capabilities, making it suitable for a wide range of AI application scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-performance Edge Computing Module: \u003c\/strong\u003eThe NVIDIA Jetson Orin Nano edge computing module is equipped with a six-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (including 32 Tensor Cores), which can run multiple AI application pipelines simultaneously to improve AI performance.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eFull-Scale Model Private Deployment: \u003c\/strong\u003eIt supports private deployment of modern mainstream AI models, including large language models such as LLaMA, ChatGLM, and Qwen, basic visual models such as ViT, Grounding DINO, and SAM, and AIGC models such as Stable Diffusion V1.5 for image generation.\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupports Up to 4K Video Decoding: \u003c\/strong\u003eIt can decode 11 channels of 1080p30 videos and supports: 1 x 4K60, 2 x 4K30, 5 x 1080p60. It meets the needs of various AI-driven visual applications.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAluminum Alloy Enclosure with Passive Heat Dissipation:\u003c\/strong\u003e The device adopts industrial-grade aluminum alloy housing and has efficient fanless passive heat dissipation function, ensuring stable operation around the clock and meeting various industrial application requirements. Its space-saving design supports wall-mounting and can be flexibly installed on walls or industrial automation equipment.\u003cbr\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eEdge Generative AI: \u003c\/strong\u003eThe NVIDIA Jetson Orin series provides powerful AI computing capabilities, large unified memory, and a comprehensive software stack to execute the latest generative AI applications with ultra-efficiency. It can quickly infer any Transformer-based generative AI model and achieve excellent edge performance in MLPerf benchmarks.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack and Ecosystem: \u003c\/strong\u003eDemocratize edge AI and robotics development with a complete AI software stack and ecosystem, powered by Edge-Generated AI, NVIDIA Metropolis, and the Isaac platform. NVIDIA JetPack, Isaac ROS, and reference AI workflows enable you to integrate advanced technologies into your products without relying on expensive in-house AI resources.\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWide Range of Applications: \u003c\/strong\u003eApplicable to industries such as edge computing, robotics, large-scale model positioning, smart cities, smart medical care, and smart industrial applications.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp style=\"font-weight: bold;\"\u003e\u003cstrong\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ec-orin_inter.webp?v=1750058577\" alt=\"\"\u003e\u003c\/strong\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"8G RAM+128G SSD without WiFi","offer_id":51090963169420,"sku":null,"price":509.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+128G SSD with WiFi","offer_id":51090963202188,"sku":null,"price":539.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD without WiFi","offer_id":51090963234956,"sku":null,"price":629.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM+256G SSD with WiFi","offer_id":51090963267724,"sku":null,"price":639.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/EC-OrinNano_-800800-1_2.jpg?v=1782727695"},{"product_id":"csb1-n10norinnano-computing-power-server-400t-large-model-privatization-deployment-bmc-nvidia","title":"CSB1-N10NOrinNano Jetson Orin Nano AI Server","description":"\u003cp\u003eMachines with deployed DeepSeek specifications come with deployment software and model files for DeepSeek-R1 series distillation models, allowing you to quickly run the reasoning of DeepSeek-R1 series distillation models at hand\u003c\/p\u003e\n\u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__02_cca198c2-c0d3-4c69-b139-98235480b817.png?v=1737095337\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__03_d0b5a512-7bce-4f76-9d3f-1dafdbbed1bb.png?v=1737095337\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__04.png?v=1732703190\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__05_da6dda4c-c88f-44e8-9f73-2eb11d7a7bcb.png?v=1737095337\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__06.png?v=1732703187\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__07.png?v=1732703190\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__08.png?v=1732703188\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__09_5792e34d-b8a6-4923-b029-f76c2fd6810b.png?v=1737095337\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNano-_-__10.png?v=1732703185\"\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"8G RAM+128G ROM \/ 10 computing nodes","offer_id":51090980503692,"sku":null,"price":7389.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G ROM \/ 10 computing nodes","offer_id":51090980536460,"sku":null,"price":7849.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/800800-1_7958bafa-2987-4824-9c88-ef3b6d1b506e.jpg?v=1782727702"},{"product_id":"csb1-n10norinnx-computing-server-1000t-large-model-privatization-deployment-bmc-nvidia","title":"CSB1-N10NOrinNX Jetson Orin NX Server","description":"\u003cdiv style=\"text-align: left;\"\u003eMachines with deployed DeepSeek specifications come with deployment software and model files for DeepSeek-R1 series distillation models, allowing you to quickly run the reasoning of DeepSeek-R1 series distillation models at hand\u003c\/div\u003e\n\u003cdiv style=\"text-align: left;\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__02_c1777213-91d1-4c17-bfb0-26df23c9ece7.png?v=1737095184\"\u003e\u003c\/div\u003e\n\u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__03_5c12fd70-1c12-419e-8ef4-9bacf7517c48.png?v=1737095214\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__04.png?v=1732703928\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__05_bd56dfbc-b993-4cdd-a8c5-b249367e5c9a.png?v=1737095233\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__06.png?v=1732703926\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__07.png?v=1732703929\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__08.png?v=1732703928\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__09_e1e97501-ac49-42e9-851f-c81380f6084e.png?v=1737095269\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10NOrinNX-_-__10.jpg?v=1732703928\"\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"16G RAM+128G ROM \/ 10 computing nodes","offer_id":51090989514892,"sku":null,"price":15089.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G ROM \/ 10 computing nodes","offer_id":51090989547660,"sku":null,"price":15549.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/800800-1_4cf9b096-de55-4f6a-bc44-087f8cfdaffa.jpg?v=1782727707"},{"product_id":"orin-nx-16gb-100tops-computing-power-8-core-arm-core-board-lpddr5-260pin-nvidia-official-original","title":"Jetson Orin NX System on Module","description":"\u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/Jetson-Orin-NX_01.jpg?v=1735529417\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/Jetson-Orin-NX_02.jpg?v=1735529417\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/Jetson-Orin-NX_03.jpg?v=1735529417\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/Jetson-Orin-NX_04.jpg?v=1735529417\"\u003e\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Orin NX 16GB","offer_id":51091033030796,"sku":null,"price":769.0,"currency_code":"USD","in_stock":false},{"title":"Orin NX 16GB Kit","offer_id":51091033063564,"sku":null,"price":989.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/7_535139d3-ef5a-4233-a0f3-246cc5ee6549.jpg?v=1782727727"},{"product_id":"orin-nano-8gb-module-official-original-core-board-40tops-computing-power-btb-nvidia-nvidia","title":"Jetson Orin Nano Super Developer Kit","description":"\u003cp\u003eThe NVIDIA Jetson Orin Nano™ Super Developer Kit is a compact yet powerful computer that redefines generative AI for small edge devices. It delivers up to 67 TOPS of AI performance, a 1.7x increase over the previous generation. It seamlessly runs the most popular generative AI models, such as Vision Transformer, Large Language Model, and Vision-Language Model.\u003c\/p\u003e\n\u003cp\u003ePowered by NVIDIA AI software and a broad AI software ecosystem, it provides the most affordable and accessible platform for developers, students, and makers. Existing Jetson Orin Nano Developer Kit users can experience a performance boost simply by upgrading their software, allowing everyone to unlock new possibilities with generative AI.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/nvdam.widen.net\/s\/zkfqjmtds2\/jetson-orin-datasheet-nano-developer-kit-3575392-r2\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePerformance improvements for cutting-edge generative AI models: \u003c\/strong\u003eNVIDIA’s latest software update boosts the Jetson Orin Nano’s AI performance from 40 AI TOPs to 67 AI TOPs and memory bandwidth from 68 GB\/s to 102 GB\/s, enabling developers and enthusiasts to run a wide range of generative AI models more efficiently.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePowerful and affordable:\u003c\/strong\u003e The Jetson Orin Nano Super Developer Kit is the most powerful and affordable generative AI embedded computer.\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"8G Super Developer Kit","offer_id":51091033096332,"sku":null,"price":379.0,"currency_code":"USD","in_stock":false},{"title":"8G SoM","offer_id":51091033129100,"sku":null,"price":299.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/NVIDIA-JetsonOrin-3QTR-Front-Left-_1.webp?v=1782727727"},{"product_id":"orin-agx-official-original-core-board-module-64gb-275tops-computing-power-nvidia","title":"Jetson AGX Orin Development Kit","description":"\u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AGX-Orin__01.jpg?v=1736846067\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AGX-Orin__02.jpg?v=1736846066\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AGX-Orin__03.jpg?v=1736846066\"\u003e\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Orin AGX System on Module (64GB)","offer_id":51091041910924,"sku":null,"price":2019.0,"currency_code":"USD","in_stock":true},{"title":"Orin AGX Development Kit","offer_id":51091041943692,"sku":null,"price":2389.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/1_12a0ccbd-bd0f-4bf2-8020-15e76c455f3a.jpg?v=1782727731"},{"product_id":"gs1-n2-ai-network-video-recorder","title":"GS1-N2 AI Gateway Server","description":"\u003cp\u003eThe Firefly GS1-N2 is a high-performance 1U edge AI server featuring a unique dual-core architecture that delivers up to 157 TOPS and 8K video decoding. With 10 Gigabit PoE ports and dual SATA bays, it provides a powerful, all-in-one solution for real-time video analytics in smart security, industrial vision, and IoT applications.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/GS1-N2_Specification_EN.pdf?v=1753152745\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cdiv style=\"position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden; background: #000;\"\u003e\u003cvideo poster=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/GS1-N2_Banner.jpg?v=1754879135\" style=\"position: absolute; top: 0; left: 0; width: 100%; height: 100%;\" playsinline=\"\" controls=\"controls\"\u003e\n    \u003csource src=\"https:\/\/cdn.shopify.com\/videos\/c\/o\/v\/65d3bfc66c7b4adfbff0adcbbaa39ac3.mp4\"\u003e\u003c\/video\u003e\u003c\/div\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eDual-core Board Modular Architecture: \u003c\/strong\u003eIt adopts a dual-core heterogeneous architecture, with one core responsible for video recording and the other for AI processing, supporting real-time inference of AI models. The two core modules work independently.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eBuilt-in SAS\/SATA Hard Drive Bays: \u003c\/strong\u003eIt features two 3.5-inch\/2.5-inch SAS\/SATA drive bays, supporting SATA 3.0 HDD\/SSD or PCIe NVMe SSD expansion, allowing the device to be easily expanded to terabyte-level capacity.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupports Custom Event Detection: \u003c\/strong\u003eSupports custom event detection, such as motion detection, area intrusion detection, boundary crossing detection, object recognition, video occlusion detection, etc., and automatically alarms when an anomaly is detected.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 25px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ScreenShot_2026-04-28_150448_389.webp?v=1777359943\" alt=\"\"\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"RK3576 (8G+64G) \/ 1688 (8G+32G)","offer_id":51091059933324,"sku":null,"price":929.0,"currency_code":"USD","in_stock":true},{"title":"RK3576 (8G+64G) \/ OrinNano(8G+128G)","offer_id":51091059966092,"sku":null,"price":1079.0,"currency_code":"USD","in_stock":true},{"title":"RK3576 (8G+64G) \/ OrinNX(8G+128G)","offer_id":51091059998860,"sku":null,"price":1889.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/800800-1.webp?v=1782727743"},{"product_id":"aio-orinnx-nvidia-jetson-orin-nx-motherboard","title":"AIO-OrinNX Jetson Orin NX Robotics Motherboard","description":"\u003cul\u003e\u003c\/ul\u003e\n\u003cp\u003eAIO-OrinNX is equipped with NVIDIA Jetson Orin NX core module, providing up to 157 TOPS computing power, supporting private deployment of modern mainstream AI models, and supporting up to 8K video decoding. It has comprehensive connection options, including Gigabit Ethernet, dual-band WiFi, 4G\/5G, Bluetooth and multiple video I\/O interfaces, running on Linux operating system, and is very suitable for edge AI applications, robots, smart drones, smart monitoring systems and other industrial AI applications.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-OrinNano_AIO-OrinNX_Specifications_EN.pdf\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-Performance Edge Computing Module:\u003c\/strong\u003e Equipped with the NVIDIA Jetson Orin Nano edge computing module, it uses a six-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (32 Tensor Cores), which can run multiple AI application pipelines concurrently, bringing powerful AI performance.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 157 TOPS Computing Power:\u003c\/strong\u003e It has an AI performance of up to 157 TOPS and supports mainstream AI models such as Transformer and ROS robot models. It supports TensorFlow, OpenCV, JetPack, MXNet, PyTorch and other frameworks to build complex deep neural networks, and has the capabilities of object recognition, target detection and tracking, speech recognition, and visual development, adapting to a variety of AI application scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eFull-Scale Model Private Deployment:\u003c\/strong\u003e Supports private deployment of modern mainstream AI models, including large language models like LLaMA-2, ChatGLM, and Qwen; vision foundation models such as ViT, Grounding DINO, and SAM; as well as AIGC models like Stable Diffusion V1.5 for image generation.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupports Up to 8K Video Decoding: \u003c\/strong\u003eIt can decode 18 channels of 1080p@30fps videos and supports: 1x8K@30fps, 2x4K@60fps, 4x4K@30fps, 9x1080p@60fps, and 18x1080p@30fps, meeting the needs of various AI application scenarios.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eEdge Generative AI: \u003c\/strong\u003eThe NVIDIA Jetson Orin series provides powerful AI computing capabilities, large unified memory, and a comprehensive software stack to execute the latest generative AI applications with ultra-efficiency. It can quickly infer any Transformer-based generative AI model and achieve excellent edge performance in MLPerf benchmarks.\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack and Ecosystem: \u003c\/strong\u003eDemocratize edge AI and robotics development with a complete AI software stack and ecosystem, powered by Edge-Generated AI, NVIDIA Metropolis, and the Isaac platform. NVIDIA JetPack, Isaac ROS, and reference AI workflows enable you to integrate advanced technologies into your products without relying on expensive in-house AI resources.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWide Range of Applications: \u003c\/strong\u003eApplicable to industries such as edge computing, robotics, large-scale model positioning, smart cities, smart medical care, and smart industrial applications.\u003cbr\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-Orin.webp?v=1750059980\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-Orin2.webp?v=1750059995\" alt=\"\"\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"8G RAM","offer_id":51091077136524,"sku":null,"price":699.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM+128G SSD without WiFi","offer_id":51091077169292,"sku":null,"price":739.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM","offer_id":51091077202060,"sku":null,"price":1029.0,"currency_code":"USD","in_stock":false},{"title":"16G RAM+128G SSD without WiFi","offer_id":51091077234828,"sku":null,"price":1059.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD without WiFi","offer_id":51091077267596,"sku":null,"price":829.0,"currency_code":"USD","in_stock":false},{"title":"16G RAM+256G SSD without WiFi","offer_id":51091077300364,"sku":null,"price":1169.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/AIO-OrinNX1.webp?v=1782727748"},{"product_id":"aio-orinnano-nvidia-jetson-orin-nano-motherboard","title":"AIO-OrinNano Jetson Orin Nano Robotics Motherboard","description":"\u003cp\u003eAIO-OrinNano is equipped with NVIDIA Jetson Orin Nano core module, providing up to 67 TOPS computing power, supporting private deployment of modern mainstream AI models, and supporting up to 4K video decoding. It has comprehensive connection options, including Gigabit Ethernet, dual-band WiFi, 4G\/5G, Bluetooth and multiple video I\/O interfaces, running on Linux operating system, and is very suitable for edge AI applications, robots, smart drones, smart monitoring systems and other industrial AI applications.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-OrinNano_AIO-OrinNX_Specifications_EN.pdf\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eHigh-Performance Edge Computing Module:\u003c\/strong\u003e Equipped with the NVIDIA Jetson Orin Nano edge computing module (8GB version), it uses a six-core ARM CPU and a 1024-core NVIDIA Ampere architecture GPU (32 Tensor Cores), which can run multiple AI application pipelines concurrently, bringing powerful AI performance.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 67 TOPS Computing Power:\u003c\/strong\u003e It has an AI performance of up to 67 TOPS and supports mainstream AI models such as Transformer and ROS robot models. It supports TensorFlow, OpenCV, JetPack, MXNet, PyTorch and other frameworks to build complex deep neural networks, and has the capabilities of object recognition, target detection and tracking, speech recognition, and visual development, adapting to a variety of AI application scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eFull-Scale Model Private Deployment:\u003c\/strong\u003e Supports private deployment of modern mainstream AI models, including large language models like LLaMA-2, ChatGLM, and Qwen; vision foundation models such as ViT, Grounding DINO, and SAM; as well as AIGC models like Stable Diffusion V1.5 for image generation.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupports Up to 4K Video Decoding: \u003c\/strong\u003eIt can decode 11 channels of 1080p30 H.265 videos and supports: 1x4K60 (H.265), 2x4K30 (H.265), and 5x1080p60 (H.265). It meets the needs of various AI-driven visual applications.\u003cstrong\u003e\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eEdge Generative AI: \u003c\/strong\u003eThe NVIDIA Jetson Orin series provides powerful AI computing capabilities, large unified memory, and a comprehensive software stack to execute the latest generative AI applications with ultra-efficiency. It can quickly infer any Transformer-based generative AI model and achieve excellent edge performance in MLPerf benchmarks.\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack and Ecosystem: \u003c\/strong\u003eDemocratize edge AI and robotics development with a complete AI software stack and ecosystem, powered by Edge-Generated AI, NVIDIA Metropolis, and the Isaac platform. NVIDIA JetPack, Isaac ROS, and reference AI workflows enable you to integrate advanced technologies into your products without relying on expensive in-house AI resources.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eWide Range of Applications: \u003c\/strong\u003eApplicable to industries such as edge computing, robotics, large-scale model positioning, smart cities, smart medical care, and smart industrial applications.\u003cbr\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-Orin.webp?v=1750059980\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-Orin2.webp?v=1750059995\" alt=\"\"\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"8G RAM","offer_id":51091255787660,"sku":null,"price":429.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM+128G SSD without WiFi","offer_id":51091255820428,"sku":null,"price":449.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD without WiFi","offer_id":51091255853196,"sku":null,"price":569.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/AIO-OrinNX1_f12cae6c-0d6c-4cb8-a09d-ea80d166be01.webp?v=1782727880"},{"product_id":"aio-gsn1-jetson-orin-rk3576-dual-module-motherboard","title":"AIO-GS1N2 Jetson Orin RK3576 Dual Module Gateway Motherboard","description":"\u003cp\u003eAIO-GS1N2 adopts a dual-core heterogeneous architecture, with two system on modules running in parallel: RK3576 for general computing and Jetson Orin for real-time AI reasoning. By utilizing heterogeneous computing and integrating the advantages of different chips, it provides high-performance and multi-functional processing capabilities for complex scenarios. This design optimizes resource allocation, supports parallel task execution, and significantly improves system efficiency.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/AIO-GS1N2_Specifications_EN.pdf?v=1749722675\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 157 TOPS Computing Power: \u003c\/strong\u003eIt supports 6-157 TOPS computing power and has the capabilities of edge computing, real-time decision-making, AI smart gateway, large-scale data forwarding processing, complex network protocols and security computing, and visual development. It is suitable for various AI application scenarios such as edge AI servers, smart gateways, industrial automation, robot control, medical equipment, and in-vehicle multimedia terminals.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSupports 8K Video Codec: \u003c\/strong\u003eSupports 8K@60fps H.265 encoding\/decoding, providing clearer and smoother video transmission over standard networks while reducing storage requirements. Strong compression efficiency makes it ideal for security surveillance, industrial IoT monitoring and other bandwidth-sensitive applications.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOnboard SATA 3.0 \/ M.2 PCIe Interfaces:\u003c\/strong\u003e Onboard SATA 3.0 and M.2 PCIe interfaces support storage expansion with 3.5\"\/2.5\" SSDs\/HDDs and PCIe NVMe SSDs, delivering terabyte-scale capacity.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e10 Gigabit Ethernet Ports with PSE Support: \u003c\/strong\u003eThis configuration features a 10 Gigabit Ethernet interface with Power Sourcing Equipment (PSE) functionality, providing strong compatibility to connect major brands of network cameras that comply with ONVIF and RTSP standards.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eApplications\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eEnterprise Security\u003c\/li\u003e\n\u003cli\u003eTraffic Management\u003c\/li\u003e\n\u003cli\u003ePublic Safety\u003c\/li\u003e\n\u003cli\u003eEnvironmental Protection\u003c\/li\u003e\n\u003cli\u003eSmart Cities\u003c\/li\u003e\n\u003cli\u003eHome Security\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 20px;\"\u003e\u003cstrong\u003eHardware Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/face_en123.webp?v=1749721305\"\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"Orin Nano 8G and RK3576 8G RAM + 64G ROM \/ With POE","offer_id":51091300909196,"sku":null,"price":919.0,"currency_code":"USD","in_stock":true},{"title":"Orin Nano 8G and RK3576 8G RAM + 64G ROM \/ Without POE","offer_id":51091300941964,"sku":null,"price":899.0,"currency_code":"USD","in_stock":true},{"title":"Orin NX 16G and RK3576 8G RAM + 64G ROM \/ With POE","offer_id":51091300974732,"sku":null,"price":1699.0,"currency_code":"USD","in_stock":true},{"title":"Orin NX 16G and RK3576 8G RAM + 64G ROM \/ Without POE","offer_id":51091301007500,"sku":null,"price":1679.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/AIO-GSN11.webp?v=1782727916"},{"product_id":"ec-agxorin-jetson-agx-orin-egde-computer","title":"EC-AGXOrin Jetson AGX Orin Egde Computer","description":"\u003cp\u003eThe EC-AGXOrin features an NVIDIA Jetson AGX Orin (64GB) module, delivering up to 275 TOPS of computing power and supporting various large-scale AI models and deep learning frameworks. It supports 22-channel 1080p video decoding and 16-channel 1080p video encoding. Its industrial-grade all-aluminum casing and dual cooling fan design ensure stable 24\/7 operation.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/EC-AGXOrin_Specification_EN.pdf?v=1764646268\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Wiki: \u003ca href=\"https:\/\/wiki.t-firefly.com\/en\/EC-AGXOrin\/preface.html\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eEquipped with NVIDIA Jetson Module: \u003c\/strong\u003eIt features an NVIDIA Jetson AGX Orin (64GB) module, equipped with a 12-core CPU and a 2048-core GPU (including 64 Tensor Cores) based on the NVIDIA Ampere architecture. It delivers powerful inference performance, providing robust computing capabilities for edge AI computing, intelligent robots, and other scenarios.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePrivate Deployment of AI Models: \u003c\/strong\u003eIt supports private deployment of mainstream large-scale AI models, including the ROS robot model; large language models based on the Transformer architecture; large vision models such as EfficientVIT, NanoOWL, NanoSAM, SAM, and TAM; and image generation models such as the Flux and Stable Diffusion series.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMultiple Deep Learning Frameworks: \u003c\/strong\u003eIt supports the Ollama framework for local deployment of large models, the ComfyUI workflow framework for AI image generation, and deep learning frameworks accelerated by cuDNN, including PaddlePaddle, PyTorch, TensorFlow, MATLAB, MxNet, and Keras. Furthermore, it supports custom operator development and Docker containerization management technology.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAI Software Stack and Ecosystem:\u003c\/strong\u003e A complete AI software stack and ecosystem powered by edge generative AI and NVIDIA Metropolis and Isaac™.\u003cbr\u003e\n\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 22 Channels of 1080P Video Decoding: \u003c\/strong\u003eSupports up to 22 channels of 1080P@30fps or 1 channel of 8K@30fps video decoding, and 16 channels of 1080P@30fps or 2 channels of 4K@60fps video encoding.\u003cbr\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ScreenShot_2025-12-02_114601_107.webp?v=1764647227\"\u003e\u003c\/strong\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"64G RAM+64G ROM","offer_id":51091570262156,"sku":null,"price":3419.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/2102-1250-max.webp?v=1782728140"},{"product_id":"csb1-n4agxorin-jetson-agx-orin-ai-server","title":"CSB1-N4AGXOrin Jetson AGX Orin 1U AI Server","description":"\u003cp\u003eThe CSB1-N4AGXOrin can be configured with up to four NVIDIA Jetson AGX Orin (64 GB) compute modules, providing up to 1100 TOPS (INT8) of computing power. It supports private deployments of mainstream AI models and various deep learning frameworks. The device is equipped with four 10 Gigabit Ethernet ports and supports expansion via SATA 3.0 hard drives.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/CSB1-N10_Specification_EN.pdf?v=1767579950\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePrivate Deployment of AI Models:\u003c\/strong\u003e It supports private deployment of mainstream large-scale language models (such as Gemma, Llama, Qwen, etc.), large-scale visual models (such as EfficientVIT, SAM, TAM, etc.), image generation models (such as Flux, Stable Diffusion, etc.), and other large-scale models.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMultiple Deep Learning Frameworks:\u003c\/strong\u003e Supports local large-scale models in Ollama and the ComfyUI graph deployment framework; compatible with various deep learning frameworks accelerated by cuDNN, including PaddlePaddle, PyTorch, TensorFlow, MATLAB, MXNet, and Keras; supports custom operator development and Docker containerization management technology.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eVideo Encoding:\u003c\/strong\u003e Supports decoding up to 1 channel 8K@30fps, 3 channels 4K@60fps and 11 channels 1080P@60fps video, as well as encoding 2 channels 4K@60fps and 8 channels 1080P@60fps video.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e4-port 10 Gigabit SFP+ Network Interface:\u003c\/strong\u003e It features four 10Gbps SFP+ Ethernet ports. Additionally, it includes a dedicated BMC management network interface for separating management and data traffic.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eIncludes aBMC Management System:\u003c\/strong\u003e Equipped with an advanced aBMC intelligent management system. Supports secondary development based on customized needs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ScreenShot_2025-12-17_170353_269.webp?v=1765962494\" alt=\"\"\u003e\u003c\/strong\u003e\u003c\/p\u003e","brand":"Firefly","offers":[{"title":"AGX Orin*4","offer_id":51091571998860,"sku":null,"price":14119.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/2723-1024.webp?v=1782728149"},{"product_id":"ec-thort5000-computers","title":"EC-ThorT5000 Jetson AGX Thor Computer","description":"\u003cp\u003eThe EC-ThorT5000 utilizes the NVIDIA Jetson Thor series Jetson T5000 module, achieving a computing power of up to 2070 TFLOPS and supporting various large AI models and deep learning frameworks. It supports 92-channel 1080P video decoding and 50-channel 1080P video encoding. It features four 10 Gigabit Ethernet ports and four Gigabit Ethernet ports. Employing an industrial-grade all-aluminum alloy casing and dual cooling fans, it ensures stable operation 24\/7.\u003c\/p\u003e\n\u003cp\u003eWidely applicable to edge computing, robotics, large model localization, smart cities, smart healthcare, smart industry, and other fields.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\u003cstrong\u003eProduct Datasheet: \u003ca href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/EC-ThorT5000_Specification_EN.pdf?v=1769656010\"\u003eClick Here\u003c\/a\u003e\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eFeature\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eEquipped with NVIDIA Jetson Module\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003ePrivate Deployment of Mainstream AI Models\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eMultiple Deep Learning Frameworks\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eAI Software Stack and Ecosystem\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eJetPack 7 with SBSA-Aligned Architecture\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eUp to 92 Channels of 1080P Video Decoding\u003c\/strong\u003e\u003c\/li\u003e\n\u003cli style=\"font-weight: bold;\"\u003e\u003cstrong\u003eFour 10-Gigabit Ethernet Ports\u003c\/strong\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2 style=\"font-size: 23px;\"\u003e\u003cstrong\u003eProduct Overview\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cdiv style=\"text-align: left;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/ScreenShot_2026-01-29_110753_687.webp?v=1769656242\" alt=\"EC-ThorT5000 Jetson AGX Thor Computer\" style=\"margin-bottom: 16px; float: none;\"\u003e\u003c\/div\u003e","brand":"Firefly","offers":[{"title":"Default Title","offer_id":51091589628044,"sku":null,"price":7019.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0779\/0732\/9164\/files\/19_1.webp?v=1782728158"}],"url":"https:\/\/www.t-firefly.com\/collections\/nvidla-jetson-family.oembed","provider":"Firefly Store","version":"1.0","type":"link"}