The Jetson AGX Xavier 64GB module makes AI-powered autonomous machines possible, running in as little as 10W and delivering up to 32 TOPs. Customers can leverage the 64GB memory to store multiple AI models, run complex applications, and enhance their real time pipelines. As part of the world’s leading AI computing platform, it benefits from the rich set of NVIDIA AI tools and workflows, enabling developers to train and deploy neural networks quickly. Jetson AGX Xavier 64GB is supported by NVIDIA JetPack SDK, which can help you save development effort and expense.

Buy Now

Technical Specifications

GPUNVIDIA Volta™ architecture with 512 NVIDIA® CUDA® cores and 64 Tensor cores
22 TOPS (INT8)
CPU8-core NVIDIA Carmel Arm®v8.2 64-bit CPU
8MB L2 + 4MB L3
DL Accelerator2x NVDLA
10 TOPS (INT8)
Vision Accelerator2x PVA
Memory64GB 256-bit LPDDR4x
136.5GB/s
Storage64GB eMMC 5.1
CSI CameraUp to 6 cameras (36 via virtual channels)
16 lanes MIPI CSI-2
D-PHY 1.2 (up to 40Gbps)
C-PHY 1.1 (up to 62Gbps)
Video Encode4x 4K60 | 8x 4K30 | 16x 1080p60 | 32x 1080p30 (H.265)
4x 4K60 | 8x 4K30 | 14x 1080p60 | 30x 1080p30 (H.264)
Video Decode2x 8K30 | 6x 4K60 | 12x 4K30 | 26x 1080p60 | 52x 1080p30 (H.265)
4x 4K60 | 8x 4K30 | 16x 1080p60 | 32x 1080p30 (H.264)
UPHY8x PCIe Gen4
3x USB 3.1
Single Lane UFS
Networking10/100/1000 BASE-T Ethernet
DisplayThree multi-mode DP 1.2a/e DP 1.4/HDMI 2.0 a/b
Other I/OUSB 2.0
UART, SPI, CAN, I2C, I2S, DMIC & DSPK, GPIOs
Power10W | 15W | 30W
Mechanical100mm x 87mm
699 pin Molex Mirror Mezz Connector
Integrated Thermal Transfer Plate

Note: Refer to the Software Features section of the latest Jetson Linux Developer Guide for a list of supported features, and the Jetson modules page for a comparison of all Jetson modules.

Questions?

Please see the FAQ and post any questions you have to the NVIDIA Jetson Developer Forum.