The Jetson TX2 is a 7.5‑Watt single‑module supercomputer that delivers true AI computing capability for edge endpoints. Built on the NVIDIA Pascal™ GPU architecture, it is equipped with 8 GB memory and a memory bandwidth of 59.7 GB/s. Featuring a rich set of standard hardware interfaces, Jetson TX2 enables easy integration into products of various types and form factors.

The NVIDIA® Jetson™ TX2 series modules deliver exceptional speed and energy efficiency for embedded AI computing devices. Powered by the NVIDIA Pascal™ GPU, with up to 8 GB memory, 59.7 GB/s memory bandwidth, and a full range of standard hardware interfaces, each supercomputer module brings genuine AI computing to the edge.



Minimal Space Footprint

You can now achieve excellent computing performance, accuracy and low power consumption on a module smaller than a credit card. Available in two form‑factors of 69.6 mm × 45 mm and 50 mm × 87 mm, Jetson TX2 series modules support deep‑learning applications for compact‑size products such as drones.

Maximize Performance

Get more than twice the performance of Jetson TX1 at half the power consumption. Featuring the NVIDIA Pascal™ GPU architecture with 256 NVIDIA® CUDA® cores and up to 8 GB memory, it enables fast computation and inference.

Optimized Energy Efficiency

Run large deep‑neural networks on edge devices with higher accuracy at power as low as 7.5 watts. Jetson TX2 series modules are well‑suited for real‑time applications with bandwidth and latency constraints, including factory robots, commercial drones and enterprise collaboration devices.

JETSON TX2 for Diverse Applications

The embedded Jetson TX2 series of expansion modules delivers up to 2.5× the performance of Jetson Nano with power consumption as low as 7.5 W. Jetson TX2 NX is pin‑ and form‑factor‑compatible with Jetson Nano, while Jetson TX2, TX2 4GB and TX2i share the original Jetson TX2 form‑factor. The rugged Jetson TX2i is ideal for building equipment such as industrial robots and medical devices.