Skip to main content
Loading...

NVIDIA Jetson TX2 4GB Module NVIDIA Jetson TX2 4GB Module with 256-Core Pascal GPU and 16GB eMMC

The Jetson TX2 4GB Module is the lower-memory version in the NVIDIA Jetson TX2 series, with the same 256-core Pascal GPU and 6-core CPU as the TX2 but 4 GB of LPDDR4, 16 GB of eMMC and no on-module Wi-Fi. NVIDIA lists it as end of life since January 2025, so it suits replacements in existing TX2 4GB designs.

  • 4GB LPDDR4 and 16GB eMMC: 128-bit LPDDR4 at up to 1600 MHz with 16 GB of eMMC 5.1, half the memory and storage of the TX2 8GB.
  • 256-Core Pascal GPU: A Pascal GPU at up to 1.12 GHz with CUDA support and a 1.4 Gpix/s ISP for camera pipelines.
  • Denver 2 and Cortex-A57 CPU: Two Denver 2 cores and four Cortex-A57 cores at up to 2.0 GHz in a heterogeneous CPU complex.
  • Two SD/SDIO at Connector: Two SD/SDIO interfaces at the 400-pin connector, against one on the TX2 8GB, with no Wi-Fi on module.
  • End of Life January 2025: NVIDIA lists the TX2 4GB as end of life since January 2025; moving to Orin needs a new carrier board.
View Jetson TX2 Series
UK Support Team: +44 (0)1785 558 300 Call
Select section
  • Overview
  • Specifications
  • Downloads

Jetson TX2 4GB Module Overview

Cost-sensitive TX2 products often shipped on the 4GB module, and keeping them in production means sourcing the same part. The Jetson TX2 4GB Module is the lower-memory version in the NVIDIA Jetson TX2 series, next to the 8GB Jetson TX2 Module, the industrial Jetson TX2i and the Jetson TX2 NX, and suits existing designs whose software fits in 4 GB.

The Jetson TX2 4GB keeps the series compute: a 256-core Pascal GPU at up to 1.12 GHz with CUDA support, and two Denver 2 cores plus four Cortex-A57 cores at up to 2.0 GHz. Memory is 4 GB of 128-bit LPDDR4 at up to 1600 MHz, with 16 GB of eMMC 5.1. NVIDIA rates module power at 7.5 W in Max-Q and 15 W in Max-P, from a 9.0 to 19.6 V input, a narrower range than the 5.5 V lower limit of the TX2 8GB.

The 400-pin board-to-board connector carries up to six 2-lane or three 4-lane MIPI CSI-2 cameras, three USB 3.0 and three USB 2.0 ports, five PCIe lanes, a SATA port, Gigabit Ethernet, two CAN interfaces and two SD/SDIO interfaces. There is no Wi-Fi or Bluetooth on the module, so wireless sits on the carrier.

NVIDIA lists the Jetson TX2 4GB as having reached end of life in January 2025, alongside the TX2 8GB. The TX2i uses the same connector and is listed through July 2027, but it carries 8 GB and a 9.0 V minimum input, so a carrier change may still need checking. The Orin modules use different connectors, so migration means a new carrier board, typically for the Jetson Orin Nano or Orin NX. Our TX2 end-of-life and migration guide covers the options.

Jetson TX2 4GB Module Specifications

Overview
Brand & ModelNVIDIA Jetson TX2 4GB Module
Performance
AI Performance1.3 TOPS
System-on-ModuleNVIDIA Jetson TX2 4GB: 1.33 TFLOPS, 256-core Pascal GPU, 2-core NVIDIA Denver 2 + 4-core Arm Cortex-A57 2.0GHz, 4GB 128-bit LPDDR4, 16GB eMMC, 7.5-15W

NVIDIA Jetson Modules

We supply NVIDIA Jetson modules fitted, imaged and tested in a carrier board or system as standard, and source modules for production and last-time-buy needs. The Jetson TX2 4GB Module belongs to our TX2 carriers and systems range.

For the board side of a replacement, see our Jetson carrier boards. For a new design on current modules, the Jetson Orin Nano range and our Orin Nano carrier boards are a common starting point.

Consult. Design. Integrate.

Things Embedded is a leading UK supplier of industrial computing and edge AI systems. We combine technical expertise with a collaborative approach to deliver optimal solutions for your application. Whether it’s an off-the-shelf platform or a custom design, we stay at the forefront of the latest technologies to ensure your success at the edge. Our team works closely with you from concept through deployment, providing guidance, engineering support, and integration expertise every step of the way.

Connect with our solutions experts today to review your requirements and find the ideal solution fit for your application.