NVIDIA JETSON AGX XAVIER | DATA SHEET | FEB19
Server-class performance in the palm of your hand.
The NVIDIA® Jetson AGX Xavier™ module delivers up to 32 TOPS of accelerated
computing capability in a compact form factor consuming under 30 Watts. This gives
you more than 20X the performance and 10X the energy efficiency of its predecessor,
the NVIDIA Jetson™ TX2.
This advanced system-on-module is powered by the NVIDIA Xavier SoC and designed
specifically for autonomous machines. Heterogeneous accelerated computing
architecture delivers advanced edge capabilities. Plus, it comes with integrated memory,
storage, power management, and an innovative thermal design to enable faster time
to market. Run modern AI workloads and solve problems in areas like manufacturing,
logistics, retail, service, agriculture, smart cities, and healthcare.
Jetson AGX Xavier is supported by NVIDIA JetPack, which includes a board support
package (BSP), Linux OS, NVIDIA CUDA®, cuDNN, and TensorRT™ software libraries for
deep learning, computer vision, GPU computing, multimedia processing,
and much more. It’s also supported by the NVIDIA DeepStream SDK, which delivers
a complete toolkit for real-time situational awareness through intelligent video analytics
(IVA). This helps you boost performance and accelerate software development, while
reducing development cost and effort.
Learn more at www.developer.nvidia.com/jetson-agx-xavier.
Module
>512-Core NVIDIA Volta™ GPU with Tensor Cores
>(2x) NVDLA Engines
>8-Core ARM® v8.2 64-Bit Carmel CPU
>16 GB 256-Bit LPDDR4x
>32 GB eMMC 5.1 Flash Storage
>7-Way VLIW Vision Accelerator Processor
Power
>Voltage Input 5 V, 9 V~20 V
>Module Power: 10 W~30 W
KEY FEATURES
Environment
>Operating Temperature: -25°C to 80°C
measured on the TTP surface
>Storage Temperature: -25°C to 80°C
>Humidity: 95% RH, -10°C to 65°C
(non-operational)
>Vibration: 5 G RMS 10 to 500 Hz
(random/ sinusoidal)
>Shock: 50 G, half sine 11 ms duration
NVIDIA JETSON
AGX XAVIER MODULE
A NEW AI MILESTONE FOR
AUTONOMOUS MACHINES
NVIDIA JETSON AGX XAVIER
TECHNICAL SPECIFICATIONS
GPU 512-Core Volta GPU with Tensor Cores
DL Accelerator (2x) NVDLA Engines
CPU 8-Core ARM v8.2 64-Bit CPU, 8 MB L2 + 4 MB L3
Memory 16 GB 256-Bit LPDDR4x | 137 GB/s
Display HDMI 2.0, eDP1.4, DP HBR3
Storage 32 GB eMMC 5.1
Vision Accelerator 7-Way VLIW Vision Processor
Encoder/Decoder (2x) 4Kp60 | HEVC/(2x) 8Kp30 | 12-Bit Support
CSI (16x) CSI-2 Lanes
PCIE/SLVS/USB/UFS (8x) PCIe Gen4 / (8x) SLVS-EC
(3x) USB 3.1
Single Lane UFS
Other UART, SPI, CAN, I2C, I2S, DMIC, GPIOs
Connectivity Gigabit Ethernet
Power 10 W~30 W
Size 87 mm x 100 mm
Mechanical 699 pin Molex Mirror Mex Connector
Integrated Thermal Transfer Plate
Visit www.developer.nvidia.com/jetson-agx-xavier to learn more.
© 2019 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo, Jetson, Xavier, AGX Xavier, CUDA, and NVIDIA Volta are trademarks and/or
registered trademarks of NVIDIA Corporation in the U.S. and other countries. Other company and product names may be trademarks of the respective
companies with which they are associated. ARM, AMBA and ARM Powered are registered trademarks of ARM Limited. Cortex, MPCore and Mali are
trademarks of ARM Limited. All other brands or product names are the property of their respective holders. “ARM” is used to represent ARM Holdings
plc; its operating company ARM Limited; and the regional subsidiaries ARM Inc.; ARM KK; ARM Korea Limited.; ARM Taiwan Limited; ARM France SAS;
ARM Consulting (Shanghai) Co. Ltd.; ARM Germany GmbH; ARM Embedded Technologies Pvt. Ltd.; ARM Norway, AS and ARM Sweden AB. FEB19
