NVIDIA Jetson AGX Orin, ConnectX-6, up to 100GbE, PCIe Gen4, SBC Profile

  • Orin Industrial, embedded Ampere GPU with 2048 CUDA cores and 64 Tensor cores
  • Embedded 12-core NVIDIA Cortex ARM64 CPU, 2.2GHz
  • ConnectX-6, provides up to 100GbE, PCIe Gen4
  • 1TB NVMe on board, SATA Gen2 interface
  • Module power: configurable from 70W - 110W


The VPX3U-ORIN-CX6-SBC module meets the needs of demanding C5ISR applications, providing a secure compute node which provides advanced AI and HPC processing capabilities, high data transfer rates, and the cyber security features required to ensure data is being protected. This autonomous SOSA™ aligned module is powered by an NVIDIA® Jetson AGX Orin™ Industrial and an NVIDIA® ConnectX®- 6 SmartNIC.

The NVIDIA Orin’s embedded Ampere GPU provides the CUDA cores and Tensor cores for data processing, deep learning inference, machine vision, audio processing and video encoding/decoding. The 2048 CUDA cores provide HPC processing, while the 64 Gen3 Tensor cores provide the architecture required for AI processing, with increased efficiency provided by new data types and sparsity.

The NVIDIA ConnectX-6 SmartNIC provides secure, high-speed network data transfer and a configurable PCIe switch. ConnectX-6 is ideal to meet the high data transfer and security requirements for C5ISR tasks. The ConnectX 6 also provides support for RDMA over Converged Ethernet (RoCE) and support for NVIDIA GPUDirect, enabling the fastest method for transferring data across the network to the GPU.

Unlocking the best performance requires the best cooling capability. WOLF’s advanced cooling technology is designed to move heat using a low weight, high efficiency paths from the hot chips to the wedgelocks.


WOLF-14T2 3U VPX Module

Product Options

WOLF modules come with factory configuration options to meet your requirements.
Contact WOLF to discuss MCOTS and custom design services if more extensive modifications are required.



Additional AGX Orin Features

  • MST DisplayPort or HDMI output
  • 2x Deep Learning Accelerator (DLA) v2 engines
  • Vision Accelerator engine for 7-way VLIW Vision Processor v2
  • Dedicated programmable audio processor
  • 2x HEVC (H.265) and AVC (H.264) NVENC and NVDEC with up to 4K-UHD encode resolution
  • 64 GB LPDDR5, 256-bit, up to 205 GB/s
  • CUDA® 12, OpenGL® 4.6, OpenGL ES 3.2, Vulkan™ 1.3

Connectivity / System Management

  • Storage: NVMe 1TB on board, SATA Gen2 (3 Gbps) interface on P2
  • ConnectX-6 PCIe Gen4 Switch, configurable, x8 or bifurcate down to x4 + x4, or down to x2
  • Backplane Ethernetzz; 40/100GBASE-KR4 and 10GBASE-KR data plane support; supports RoCE
  • 1000BASE-T Ethernet
  • USB 3.2 and USB 2.0
  • Advanced Jetson security features
  • Switching is offloaded from the CPU and run on the ConnectX hardware with NVIDIA ASAP2 technology
  • On-board IPMI controller for system management
  • Removable front panel for setup/test/debug
  • WOLF BSP with Jetson Linux and JetPack SDK


Mechanical / Open Systems Architecture

  • High level of ruggedization:
    • Operating temperature: -40° to +80°C
    • Vibration (sine wave): 10G peak, 5 - 2000Hz
    • Shock: 40G peak 
  • Dimensions: 160mm x 100mm x 25.4mm
  • Weight: 1.34 kg
  • ANSI/VITA 48, 65 (VPX REDI, OpenVPX)
  • SOSA™ Aligned SBC slot profile 14.2.16



Open the product datasheet - includes block diagram, order codes, etc.



Stay current. Subscribe.

* indicates required





This website uses cookies. Please see our Privacy Policy for more information.