Hardware For Every Situation
High-performance, low-power NVIDIA® Jetson™ systems give you real-time artificial intelligence (AI) performance where you need it most—at the edge. Processing of complex data can now be done on-board small, power-efficient devices, so you can count on fast, accurate inference in network-constrained environments.
NVIDIA Jetson Developer Kits and modules, together with NVIDIA JetPack SDK, provide everything you need to develop and deploy applications for multiple use cases using one unified software architecture. This dramatically reduces software development costs and gives you a scalable AI strategy for autonomous machines.
AI at the edge unlocks tremendous potential in everything from healthcare to manufacturing to agriculture—and beyond.
|Jetson TX1||Jetson TX2||Jetson AGX Xavier|
|AI Performance||1 TOPs||1.3 TOPs||32 TOPs|
|GPU||NVIDIA Maxwell™ GPU with 256 NVIDIA CUDA® Cores||NVIDIA Pascal™ GPU with 256 NVIDIA CUDA Cores||512-core NVIDIA Volta™ GPU with Tensor Cores|
|CPU||Quad-Core ARM® Cortex®-A57 MPCore Processor||Dual-Core Denver 2 64-bit CPU and Quad-Core ARM A57 Complex||8-Core ARM v8.2 64-bit NVIDIA Carmel CPU|
|Memory||4GB LPDDR4 Memory||4GB 128-bit LPDDR4 Memory||8GB 128-bit LPDDR4 Memory||8GB 128-bit LPDDR4 (ECC support)||16GB 256-Bit LPDDR4x | 137 GB/s|
|Storage||16GB eMMC 5.1||16GB eMMC 5.1||32GB eMMC 5.1||32GB eMMC 5.1||32GB eMMC 5.1|
|Power||Under 10W||7.5W / 15W||10W / 20W||10W / 15W / 30W|
|PCIE||Gen 2 | 1x4 + 1x1||Gen 2 | 1x4 + 1x1 OR 2x1 + 1x2||x8 Gen 4 (RootPort + EndPoint) 2 x x1 + 1 x x2 + 1 x x4 Gen 3/4|
|CSI||12x CSI2 D-PHY 1.1 lanes (1.5 Gbps/Lane)||12x CSI2 D-PHY 1.1 lanes (2.5 Gbps/Lane)||
16x CSI2 D-PHY 1.2 lanes (2.5 Gbps/Lane)
x8 SLVS-EC lanes (2034 Mpbps)
|DL Accelerator||—||—||(2x) NVDLA Engines*|
|Vision Accelerator||—||—||7-Way VLIW Vision Processor*|
Jetson AGX Xavier
NVIDIA Jetson AGX Xavier is the latest addition to the Jetson platform. It’s the world's first AI computer for autonomous machines, delivering the performance of a GPU workstation in an embedded module under 30W. With multiple operating modes at 10W, 15W, and 30W, Jetson AGX Xavier has greater than 10X the energy efficiency and more than 20X the performance of the Jetson TX2.
Jetson TX2 is built around an NVIDIA Pascal-family GPU and features a variety of standard hardware interfaces that make it easy to integrate it into a wide range of products and form factors. The Jetson TX2 embedded module for edge AI applications comes in three versions: Jetson TX2, Jetson TX2i, and the upcoming, lower-cost Jetson TX2 4GB. Jetson TX1-based products can migrate to the more powerful Jetson TX2 4GB at the same price.
The world's first supercomputer on a module, Jetson TX1 delivers the performance and power efficiency needed for the latest visual computing applications. It's built around the revolutionary NVIDIA Maxwell architecture with 256 CUDA cores delivering over 1 FLOPs of performance. It also includes 64-bit CPUs, 4K video encode and decode capabilities, and a camera interface capable of 1400 MPix/s to enable embedded deep learning, computer vision, graphics, and GPU computing systems.
No matter where you are in the design process, we make it easy to find the right hardware documents you need. Follow the links below to get started.
Please Note: Some documents require that you’re a member of the NVIDIA Developer Program for download. If you aren’t already a member, join the Developer Program now.