{"title":"Edge Computing (NVIDIA)","description":"","products":[{"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":42231437131860,"sku":null,"price":1089.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+128G SSD \/ Deepseek Deployed without Wifi","offer_id":42231474061396,"sku":null,"price":1109.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM+256G SSD \/ Standard without Wifi","offer_id":45300359069780,"sku":null,"price":1199.0,"currency_code":"USD","in_stock":false},{"title":"16G RAM+256G SSD \/ Deepseek Deployed without Wifi","offer_id":45300359102548,"sku":null,"price":1209.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/800800-1.jpg?v=1741070889"},{"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":42231535829076,"sku":null,"price":479.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+128G SSD \/ Deepseek Deployed without Wifi","offer_id":42231535861844,"sku":null,"price":499.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD \/ Standard without Wifi","offer_id":45300305756244,"sku":null,"price":599.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM+256G SSD \/ Deepseek Deployed without Wifi","offer_id":45300305789012,"sku":null,"price":619.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/800800-1_03c4016b-006a-45e0-9ae7-4875f2eb8425.jpg?v=1741575816"},{"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":42073385500756,"sku":"","price":1149.0,"currency_code":"USD","in_stock":false},{"title":"16G RAM +128G SSD Without wifi","offer_id":42073384124500,"sku":"","price":1119.0,"currency_code":"USD","in_stock":true},{"title":"16G RAM Without Wifi And SSD","offer_id":42186849714260,"sku":"","price":1089.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM +128G SSD With wifi","offer_id":42073406341204,"sku":"","price":819.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM +128G SSD Without wifi","offer_id":42073406308436,"sku":"","price":789.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM Without Wifi And SSD","offer_id":42186849747028,"sku":"","price":749.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/EC-OrinNX_-800800-2_e506d917-f7c1-49e2-8582-b812f7ae6e23.jpg?v=1731554576"},{"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":42073383600212,"sku":"","price":509.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+128G SSD with WiFi","offer_id":41695706251348,"sku":"","price":539.0,"currency_code":"USD","in_stock":true},{"title":"8G RAM+256G SSD without WiFi","offer_id":45300287602772,"sku":null,"price":629.0,"currency_code":"USD","in_stock":false},{"title":"8G RAM+256G SSD with WiFi","offer_id":45300287635540,"sku":null,"price":639.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/EC-OrinNano_-800800-1_2.jpg?v=1731567158"},{"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":42730714660948,"sku":null,"price":3419.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/2102-1250-max.webp?v=1764645835"},{"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":42880980287572,"sku":null,"price":7019.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0592\/4965\/5892\/files\/19_1.webp?v=1769650646"}],"url":"https:\/\/www.firefly.store\/collections\/edge-computing-nvidia.oembed","provider":"Firefly Store","version":"1.0","type":"link"}