NVIDIA® Jetson™ TX2 gives you exceptional speed and power-efficiency in an embedded AI computing device. This supercomputer-on-a-module brings true AI computing at the edge with an NVIDIA Pascal™ GPU, up to 8 GB of memory, 59.7 GB/s of memory bandwidth, and a wide range of standard hardware interfaces that offer the perfect fit for a variety of products and form factors.

A JETSON TX2 FOR ANY APPLICATION

The extended Jetson family of embedded modules includes the lower-price Jetson TX2 4GB, which provides a powerful migration path for Jetson TX1 users, the Jetson TX2, which is a 7.5-watt supercomputer on a module that brings true AI computing at the edge, and the Jetson TX2i, whose rugged design is ideal for settings including industrial robots and medical equipment.

The NVIDIA Jetson TX2 Developer Kit gives you a fast, easy way to develop hardware and software for the Jetson TX2 AI supercomputer on a module. It exposes the hardware capabilities and interfaces of the module and is supported by NVIDIA Jetpack—a complete SDK that includes the BSP, libraries for deep learning, computer vision, GPU computing, multimedia processing, and much more.

BUY NOW

TECHNICAL SPECS

GPU NVIDIA Pascal architecture with 256 NVIDIA CUDA cores
1.3 TFLOPS (FP16)
CPU Dual-core Denver 2 64-bit CPU and quad-core ARM A57 complex
Memory 8 GB 128-bit LPDDR4
1866MHz – 59.7 GB/s
Storage 32GB eMMC 5.1
Encoder 500 MP/sec
1x 4K @ 60 (HEVC)
3x 4K @ 30 (HEVC)
4x 1080p @ 60 (HEVC)
8x 1080p @ 30 (HEVC)
Decoder 1000 MP/sec
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
7x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)

*Refer to NVIDIA documentation to see what is supported currently.

Dev Kit I/Os Jetson TX2 Module Interface
PCIe Gen 2 | 1×4 + 1×1 OR 2×1 + 1×2
USB USB 3.0 + USB 2.0
Camera Up to 6 cameras (2 Lane)
CSI2 D-PHY 1.2 (2.5 Gbps/Lane)
Networking 801.11ac WLAN and Bluetooth connectivity
Display HDMI
Other GPIO, I2 C, I2 S, SPI, CAN, UART

Explore new AI capabilities at the edge with the NVIDIA Jetson TX2 4GB. This embedded computer lets you run neural networks with double the compute performance or double the power efficiency of Jetson TX1—at the same price.

BUY NOW

TECHNICAL SPECS

GPU NVIDIA Pascal architecture with 256 NVIDIA CUDA cores
1.3 TFLOPS (FP16)
CPU Dual-core Denver 2 64-bit CPU and quad-core ARM A57 complex
Memory 4 GB 128-bit LPDDR4 | 1600 MHz – 51.2 GBs
Display HDMI 2.0 / eDP 1.4 / 2x DSI / 2x DP 1.2
Storage 16GB eMMC 5.1
Video Encode 500 MP/sec
1x 4K @ 60 (HEVC)
3x 4K @ 30 (HEVC)
4x 1080p @ 60 (HEVC)
8x 1080p @ 30 (HEVC)
Video Decode 1000 MP/sec
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
7x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)
Camera 12 lanes MIPI CSI-2, D-PHY 1.2 (30 Gbps)
UPHY Gen 2 | 1×4 + 1×1 OR 2×1 + 1×2, USB 3.0 + USB 2.0
Other UART, SPI, CAN, I2C, I2S, DMIC, GPIOs
Networking 10/100/1000 BASE-T Ethernet | Wi-Fi requires external chip
Size 87 mm x 50 mm
Mechanical 400-pin connector with Thermal Transfer Plate (TTP)

*Refer to NVIDIA documentation to see what is supported currently.

Jetson TX2 is a 7.5-watt supercomputer on a module that brings true AI computing at the edge. It’s built around an NVIDIA Pascal-family GPU and loaded with 8 GB of memory and 59.7 GB/s of memory bandwidth. It features a variety of standard hardware interfaces that make it easy to integrate it into a wide range of products and form factors.

BUY NOW

TECHNICAL SPECS

GPU NVIDIA Pascal architecture with 256 NVIDIA CUDA cores
1.3 TFLOPS (FP16)
CPU Dual-core Denver 2 64-bit CPU and quad-core ARM A57 complex
Memory 8 GB 128-bit LPDDR4 | 1866MHz – 59.7 GB/s
Display HDMI 2.0 / eDP 1.4 / 2x DSI / 2x DP 1.2
Storage 32GB eMMC 5.1
Video Encode 500 MP/sec
1x 4K @ 60 (HEVC)
3x 4K @ 30 (HEVC)
4x 1080p @ 60 (HEVC)
8x 1080p @ 30 (HEVC)
Video Decode 1000 MP/sec
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
7x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)
Camera 12 lanes MIPI CSI-2, D-PHY 1.2 (30 Gbps)
UPHY Gen 2 | 1×4 + 1×1 OR 2×1 + 1×2, USB 3.0 + USB 2.0
Other UART, SPI, CAN, I2C, I2S, DMIC, GPIOs
Networking 10/100/1000 BASE-T Ethernet | Wi-Fi onboard
Size 87 mm x 50 mm
Mechanical 400-pin connector with Thermal Transfer Plate (TTP)

*Refer to NVIDIA documenetation to see what is supported currently.

Jetson TX2i module’s rugged design, small form factor, and reduced power envelope make it ideal for high-performance edge computing devices such as industrial robots, machine vision cameras, and portable medical equipment.

BUY NOW

TECHNICAL SPECS

GPU NVIDIA Pascal architecture with 256 NVIDIA CUDA cores
1.3 TFLOPS (FP16)
CPU Dual-core Denver 2 64-bit CPU and quad-core ARM A57 complex
Memory 8 GB 128-bit LPDDR4
1600MHz – 51.2 GB/s
Display HDMI 2.0 / eDP 1.4 / 2x DSI / 2x DP 1.2
Storage 32GB eMMC 5.1
Video Encode 500 MP/sec
1x 4K @ 60 (HEVC)
3x 4K @ 30 (HEVC)
4x 1080p @ 60 (HEVC)
8x 1080p @ 30 (HEVC)
Video Decode 1000 MP/sec
2x 4K @ 60 (HEVC)
4x 4K @ 30 (HEVC)
7x 1080p @ 60 (HEVC)
14x 1080p @ 30 (HEVC)
Camera 12 lanes MIPI CSI-2, D-PHY 1.2 (30 Gbps)
UPHY Gen 2 | 1×4 + 1×1 OR 2×1 + 1×2, USB 3.0 + USB 2.0
Other UART, SPI, CAN, I2C, I2S, DMIC, GPIOs
Networking 10/100/1000 BASE-T Ethernet | Wi-Fi requires external chip
Size 87 mm x 50 mm
Mechanical 400-pin connector with Thermal Transfer Plate (TTP)

*Refer to NVIDIA documentation to see what is supported currently.