What is AGX Xavier?

The NVIDIA® Jetson™ AGX Xavier™ is the world’s first AI computer for autonomous machines.

  • 20x performance than Jetson™ TX2
  • 512-core Volta GPU and 64 Tensor cores with discreet dual Deep Learning Accelerator (DLA) NVDLA engines
  • 4 x dual-core CPU clusters (8 NVIDIA Carmel processor cores)
  • 16GB 256-bit wide LPDDR4X memory interface
  • Module Size: 100 mm x 87 mm

For further specifications, please refer to the documentation available for Jetson AGX Xavier in the
Jetson Download Center.

What is the difference between TX2 and AGX Xavier?

FeatureJetson™ TX2Jetson™ AGX Xavier 8GBJetson™ AGX Xavier
GPU256 Core Pascal @ 1.3GHz384 Core Volta @ 1.37GHz
64 Tensor Cores
512 Core Volta @ 1.37GHz
64 Tensor Cores
DL Accelerator-(2x) NVDLA(2x) NVDLA
Vision Accelerator-(2x) 7-way VLIW Processor(2x) 7-way VLIW Processor
CPU6 core Denver and A57 @ 2GHz
(2x) 2MB L2
6 core Carmel ARM CPU @ 1.3GHz
(4x) 2MB L2 + 4MB L3
8 core Carmel ARM CPU @ 2.26GHz
(4x) 2MB L2 + 4MB L3
Memory8GB 128 bit LPDDR4
58.4 GB/s
8GB 256-bit LPDDR4x @ 2133MHz
85 GB/s
16GB 256-bit LPDDR4x @ 2133MHz
137 GB/s
Storage32GB eMMC32GB eMMC32GB eMMC
Video Encode(2x) 4K @30
HEVC
2x4K @30 | 4x4K @30 | 12x1080p @60 | 24x1080p @30 (HEVC) | 16x1080p @30 (H.264)2x8K @30 | 6x4K @60 | 12x4K @30 | 26x1080p @60 | 52x1080p @30 (HEVC) | 30x1080p @30 (H.264)
Video Decode(2x) 4K @30
12 bit support
(2x) 8Kp30 / (6x) 4Kp60
12 bit support
(2x) 8Kp30 / (6x) 4Kp60
12 bit support
Camera12 lanes MIPI CSI-2
D-PHY 1.2 30Gbps
16 lanes MIPI CSI-2 | 8 lanes SLVS-EC
D-PHY 40Gbps / C-PHY 109Gbps
16 lanes MIPI CSI-2 | 8 lanes SLVS-EC
D-PHY 40Gbps / C-PHY 109Gbps
PCI Express5 lanes PCIe Gen 2
1x4 + 1x1 | 2x1 + 1x4
16 lanes PCIe Gen 3
1x8 + 1x4 + 1x2 + 2x1
16 lanes PCIe Gen 4
1x8 + 1x4 + 1x2 + 2x1
Mechanical50mm x 87mm
400 pin connector
100mm x 87mm
699 pin connector
100mm x 87mm
699 pin connector
Power7.5W / 15W10W / 20W10W / 15W / 30W

AGX Xavier Solutions