Beijing Plink AI Technology Co., Ltd |
|
100 TOPS Embedded Nvidia Ai Module Jetson Orin NX Module 16GB
NVIDIA Jetson AGX Orin NX 16GB Module
AI is Now Everywhere
As businesses across industries grapple with vast amounts of data,
more complex operations, and more dynamic markets, edge AI is
playing a growing role in helping them rapidly respond. Through a
combination of computing power, AI technology, data analytics, and
advanced connectivity, the edge extends compute capabilities from
data centers out to the edge of networks, allowing organizations to
act quickly on data where it’s captured. Reducing the distance
between where data is captured and where it’s processed not only
alleviates data transit costs, but also improves latency, bandwidth
utilization, and infrastructure costs.
Brand | NVIDIA |
Module | NVIDIA Jetson AGX Orin NX 16GB |
AI Performance | 100 TOPS |
GPU | 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores |
GPU Max Frequency | 918 MHz |
CPU | 8-core Arm® Cortex®-A78AE v8.2 64-bit CPU |
CPU Max Frequency | 2 GHz |
DLA Max Frequency | 614 MHz |
DL Accelerator | 2x NVDLA v2 |
Vision Accelerator | 1x PVA v2 |
Safety Cluster Engine | - |
Memory | 16GB 128-bit LPDDR5 |
Storage | - |
Camera | Up to 4 cameras (8 via virtual channels***) |
Video Encode | 1x 4K60 (H.265) |
Video Decode | 1x 8K30 (H.265) |
PCIe | 1 x4 + 3 x1 |
USB | 3x USB 3.2 Gen2 (10 Gbps) |
Networking | 1x GbE |
Power | 10W - 25W |
Display | 1x 8K30 multi-mode DP 1.4a (+MST)/eDP 1.4a/HDMI 2.1 |
Other I/O | 3x UART, 2x SPI, 2x I2S, 4x I2C, 1x CAN, DMIC & DSPK, PWM, GPIOs |
Mechanical | 69.6mm x 45mm |
Addressing the Requirements of Edge AI
AI at the edge comes with a unique set of requirements. Edge
systems, dispersed across vast physical distances, lack the
centrality that a data center presents. Software or system updates
either need to be performed manually or to be centrally managed to
easily deploy, manage, and scale software across vast fleets of
devices. Moreover, the security requirements for edge computing
infrastructure differ from cloud or data center computing models.
Edge locations lack the physical security that data centers have,
so an end-to-end security model that protects both the application
intellectual property and the sensor data is paramount for a
successful deployment.