NVIDIA Jetson TX2

Next-level performance for mass-market AI products.

Explore new AI capabilities with the exceptional speed and power efficiency of the NVIDIA Jetson™ TX2 series of embedded AI modules. It features a variety of standard hardware interfaces that make it easy to integrate into a wide range of products and form factors, such as factory robots, commercial drones, portable medical equipment, and enterprise collaboration devices. And it’s available in four different production modules based on the same architecture, so you get exactly what you need to bring true AI computing to the edge.

Jetson TX2 Series

Jetson TX2 series modules deliver up to 2.5X the performance of the Jetson Nano™ and are available in either 69.6mm x 45mm or 50mm x 87mm sizes. They can run large, deep neural networks for higher accuracy with double the compute performance in as little as 7.5W, are production ready, and come in 8GB, 4GB, and Industrial versions.

View Jetson TX2 Technical Specifications

  Jetson TX2 series
Jetson TX2i Jetson TX2 Jetson TX2 4GB Jetson TX2 NX
AI Performance 1.26 TFLOPS 1.33 TFLOPS
GPU 256-core NVIDIA Pascal™ architecture GPU
GPU Max Frequency 1.12GHz 1.3 GHz
CPU Dual-core NVIDIA Denver™ 2 64-bit CPU and quad-core Arm® Cortex®-A57 MPCore processor
CPU Max Frequency Denver2: 1.95 GHz
Cortex-A57: 1.92 GHz
Denver 2: 2 GHz
Cortex-A57: 2 GHz
Memory 8GB 128-bit LPDDR4 (ECC Support)
51.2GB/s
8GB 128-bit LPDDR4
59.7GB/s
4GB 128-bit LPDDR4
51.2GB/s
Storage 32GB eMMC 5.1 16GB eMMC 5.1
Video Encode 1x 4K60 (H.265)
3x 4K30 (H.265)
4x 1080p60 (H.265)
Video Decode 2x 4K60 (H.265)
7x 1080p60 (H.265)
14x 1080p30 (H.265)
CSI Camera Up to 6 cameras
(12 via virtual channels)
12 lanes MIPI CSI-2
D-PHY 1.2 (up to 30 Gbps)
Up to 5 cameras
(12 via virtual channels)
12 lanes MIPI CSI-2
D-PHY 1.1 (up to 30 Gbps)
PCIe up to 1 x1 + 1 x4 OR 1 x1 + 1 x1 + 1 x2
(PCIe Gen2)
1 x1 + 1 x2
(PCIe Gen2)
USB up to 3x USB 3.0 (5 Gbps)
3x USB 2.0
1x USB 3.0 (5 Gbps)
3x USB 2.0
Networking 1x GbE 1x GbE, WLAN 1x GbE
Display 2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0
2 x4 DSI (1.5Gbps/lane)
2 multi-mode DP 1.2/eDP 1.4/HDMI 2.0
1x 2 DSI (1.5Gbps/lane)
Other I/O 5x UART, 3x SPI, 4x I2S, 8x I2C, 2x CAN, GPIOs 3x UART, 2x SPI, 4x I2S, 4x I2C, 1x CAN, GPIOs
Power 10W - 20W 7.5W - 15W
Mechanical 87mm x 50mm
400-pin connector
Integrated Thermal Transfer Plate
69.6mm x 45mm
260-pin SO-DIMM connector
View Full Specs

Jetson Ruggedized Systems

Robotics and automation are increasingly being used in manufacturing, agriculture, construction, energy, government, and other industries. These applications often require extended temperature, shock, and vibration specifications to operate in harsh environments. The NVIDIA Jetson™ platform offers multiple options to meet the needs of these rugged applications.

Jetson Resources

Support Resources

Get the resources and support you need to create innovative AI products.

Success Stories

See how companies are using Jetson to accelerate product development.

Blogs & News

Get the latest news and stories on Jetson in action.

Jetson Forum

Discuss the latest applications and get help from other Jetson developers.

NVIDIA Jetson Partner Ecosystem

The Jetson partner ecosystem offers a wide range of AI and system software, developer tools, and custom software development. A broad range of Jetson TX2 systems and carrier boards are also available, as well as peripherals such as sensors, cameras, connectivity modules (5G, 4G, Wi-Fi), and more.

NVIDIA Software

All NVIDIA Jetson modules and developer kits are supported by the same software stack, so you can develop once and deploy everywhere. Jetson software is designed to provide end-to-end acceleration for AI applications and accelerate your time to market. This brings the same powerful NVIDIA technologies that power data centers and cloud deployments to the edge.

Pretrained Models

Many AI applications have common needs: classification, object detection, language translation, text-to-speech, recommender engines, sentiment analysis, and more. Pretrained models from the NGC™ catalog are performance-optimized and ready to be fine-tuned with the NVIDIA TAO Toolkit and customer datasets, reducing time and cost for production of AI software development.

NVIDIA Platforms for Robotics, AI Speech, and Smart Cities

NVIDIA software platforms—including Isaac™ for robotics, Riva for AI speech, and Metropolis for video analytics—are available to speed vertical-specific applications.

NVIDIA Isaac Platform for Robotics

Demand for intelligent robots is growing as more industries embrace automation to address supply chain challenges and labor force shortages. Innovators across manufacturing, retail, agriculture, logistics, warehouses, delivery, and healthcare are using the NVIDIA Isaac platform to accelerate their robotics development, simulation, and deployment.

NVIDIA Riva for Speech AI Applications

NVIDIA Riva is a fully accelerated SDK for building multimodal conversational AI applications using an end-to-end deep learning pipeline. The Riva SDK includes pretrained conversational AI models, the NVIDIA TAO Toolkit, and optimized skills for speech, vision, and natural language processing (NLP) tasks.

NVIDIA Metropolis for Vision AI Applications

NVIDIA Metropolis is an application framework, set of developer tools, and partner ecosystem. It brings visual data and AI together to improve operational efficiency and safety across a broad range of industries.