New
NVIDIA Jetson AGX Xavier Module

NVIDIA Jetson AGX Xavier Module

NVIDIA Jetson AGX Xavier Module
NVIDIA | A-000000-08171
€1,680.00
20 perc. French VAT inc.

The NVIDIA Jetson AGX Xavier is an embedded computing platform designed for edge artificial intelligence (Edge AI) applications, autonomous robotics, and advanced industrial systems.

Quantity
Contact us to find out about delivery times

Create a cart and turn it into a quote instantly!
Payment methods (see T&C)
Debit card
PayPal
Payment by invoice
Wire transfer

NVIDIA Jetson AGX Xavier – Embedded AI Module (32 GB / 64 GB)

Key features

  • High-performance module designed for advanced embedded systems
  • NVIDIA Volta GPU with 512 CUDA cores and 64 Tensor Cores
  • 8-core NVIDIA Carmel CPU for intensive processing
  • 2x NVDLA for AI workload acceleration
  • 2x PVA for advanced vision processing
  • Up to 64 GB of LPDDR4x memory depending on the version
  • Configurable power profiles: 10 W / 15 W / 30 W
  • Compatible with the NVIDIA software ecosystem: JetPack, CUDA, TensorRT, cuDNN, DeepStream, Isaac

Applications

The NVIDIA Jetson AGX Xavier targets applications requiring high computing density in a compact embedded format. It is particularly suitable for:

  • autonomous robotics
  • industrial vision and optical inspection
  • automated logistics systems
  • retail analytics and video analytics equipment
  • drones and intelligent mobile systems
  • smart city, healthcare, and industrial applications

Jetson AGX Xavier version comparison

The Jetson AGX Xavier family is available in two main versions. The 32 GB version is suited to advanced integrations already requiring strong computing capabilities, while the 64 GB version is better suited to applications running multiple AI models, more complex pipelines, or heavier concurrent workloads.

ModuleGPUCPUMemoryStoragePower Consumption
Jetson AGX Xavier 32 GBVolta – 512 CUDA + 64 Tensor Cores8-core NVIDIA Carmel Arm v8.232 GB LPDDR4x 256-bit32 GB eMMC 5.110 – 30 W
Jetson AGX Xavier 64 GBVolta – 512 CUDA + 64 Tensor Cores8-core NVIDIA Carmel Arm v8.264 GB LPDDR4x 256-bit64 GB eMMC 5.110 – 30 W

A powerful platform for robotics and Edge AI

The Jetson AGX Xavier provides high computing density for embedded systems requiring real-time processing of video streams, multiple sensors, and advanced artificial intelligence algorithms. Thanks to the NVIDIA JetPack software stack and associated libraries, it accelerates the development of robotics, computer vision, embedded AI, and video analytics applications.

Technical specifications of the NVIDIA Jetson AGX Xavier module

  • GPU Architecture: NVIDIA Volta
  • GPU: 512 CUDA cores + 64 Tensor Cores
  • AI Accelerators: 2x NVDLA
  • Vision Accelerator: 2x PVA
  • CPU: 8-core NVIDIA Carmel Arm v8.2 64-bit
  • CPU Cache: 8 MB L2 + 4 MB L3
  • AI Performance: up to 32 TOPS
  • Memory:
    • 32 GB version: 32 GB LPDDR4x, 256-bit bus, 136.5 GB/s
    • 64 GB version: 64 GB LPDDR4x, 256-bit bus, 136.5 GB/s
  • Embedded Storage:
    • 32 GB version: 32 GB eMMC 5.1
    • 64 GB version: 64 GB eMMC 5.1
  • Cameras:
    • up to 6 cameras (36 via virtual channels)
    • 16 lanes MIPI CSI-2
    • D-PHY 1.2 up to 40 Gops
    • C-PHY 1.1 up to 62 Gops
  • Video Encoding (H.265):
    • 4 x 4K60
    • 8 x 4K30
    • 16 x 1080p60
    • 32 x 1080p30
  • Video Decoding (H.265):
    • 2 x 8K30
    • 6 x 4K60
    • 12 x 4K30
    • 26 x 1080p60
    • 52 x 1080p30
  • PCI Express: 1 x8 + 1 x4 + 1 x2 + 2 x1 (PCIe Gen4, Root Port & Endpoint)
  • USB:
    • 3 x USB 3.2 Gen2 (10 Gops)
    • 4 x USB 2.0
  • Network: 1 x Gigabit Ethernet
  • Display: 3 multi-mode outputs DP 1.4 / eDP 1.4 / HDMI 2.0
  • Interfaces: 5 x UART, 3 x SPI, 4 x I2S, 8 x I2C, 2 x CAN, PWM, DMIC, GPIOs
  • Power Profiles: 10 W / 15 W / 30 W
  • Dimensions: 100 x 87 mm
  • Connector: 699-pin Molex Mirror Mezz Connector
  • Cooling: Integrated Thermal Transfer Plate

Resources for the NVIDIA Jetson AGX Xavier module

Customers who viewed this item also viewed