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.
Technical Specifications
|
|
|
||||
|---|---|---|---|---|---|---|
| TX2 4GB | TX2 | TX2i | AGX XAVIER 8GB | AGX XAVIER | ||
| AI Performance | 472 GFLOPs | 1.3 TFLOPs | 20 TOPs | 32 TOPs | ||
| GPU | 128-core NVIDIA Maxwell™ GPU | 256-core NVIDIA Pascal™ GPU | 384-core NVIDIA Volta™ GPU with 48 Tensor Cores | 512-core NVIDIA Volta™ GPU with 64 Tensor Cores | ||
| CPU | Quad-Core ARM® Cortex®-A57 MPCore | Dual-Core NVIDIA Denver 2 64-Bit CPU and Quad-Core ARM® Cortex®-A57 MPCore | 6-Core Carmel ARM v8.2 64-bit NVIDIA Carmel CPU,
8MB L2 + 4MB L3 |
8-Core Carmel ARM v8.2 64-bit NVIDIA Carmel CPU,
8MB L2 + 4MB L3 |
||
| Memory | 4GB 64-bit LPDDR4 Memory
1600MHz - 25.6 GB/s |
4GB 128-bit LPDDR4 Memory
1600 MHz - 51.2 GBs |
8GB 128-bit LPDDR4 Memory
1866MHz - 59.7 GB/s |
8GB 128-bit LPDDR4 (ECC support)
1600MHz - 51.2 GB/s |
8GB 256-Bit LPDDR4x 85.3 GB/s |
16GB 256-Bit LPDDR4x 136.5 GB/s |
| Storage | 16GB eMMC 5.1** | 16GB eMMC 5.1 | 32GB eMMC 5.1 | 32GB eMMC 5.1 | 32GB eMMC 5.1 | |
| Power | 5W / 10W | 7.5W / 15W | 10W / 20W | 10W / 20W | 10W / 15W / 30W | |
| PCIE | Gen 2 | 1x4 | Gen 2 | 1x4 + 1x1 OR 2x1 + 1x2 | 1 x8 or 1 x4 or 1 x2 or 2 x1 PCIe (Gen3) | 1 x8 or 1 x4 or 1 x2 or 2 x1 PCIe (Gen4) | ||
| CSI |
12x CSI-2 D-PHY 1.1
(Up to 18 GB/s) |
12x CSI-2 D-PHY 1.2
(Up to 30 GB/s) |
16x CSI-2 D-PHY 1.2
(Up to 40 GB/s) C-PHY 1.1 (Up to 64 GB/s) |
16x MIPI CSI-2 D-PHY 1.2
(Up to 40 GB/s) C-PHY 1.1 (Up to 109 GB/s) |
||
| Display |
Two Multi-Mode DP 1.2 eDP 1.4 HDMI 2.0 1x2 DSI (1.5Gbps/lane) |
Two Multi-Mode DP 1.2 eDP 1.4 HDMI 2.0 Two 1x4 DSI (1.5Gbps/lane) |
Three Multi-Mode DP 1.2 eDP 1.4 HDMI 2.0 No DSI support |
|||
| DL Accelerator | — | — | 4.1 TFLOPS (FP16) 8.2 TOPS (INT8)* | 5 TFLOPS (FP16) 10 TOPS (INT8) * | ||
| Vision Accelerator | — | — | 7-Way VLIW Vision Processor* | |||
| Wi-Fi | No | No | Yes | No | No | |
Jetson AGX Xavier Series
Jetson AGX Xavier series modules enable new levels of compute density, power efficiency, and AI inferencing capabilities at the edge. Users can configure operating modes for their applications at 10W or 20W with the lower-power and lower-price Jetson AGX Xavier 8GB module, or at 10W, 15W, or 30W with the Jetson AGX Xavier module. These modules have 10X the energy efficiency and 20X the performance of Jetson TX2.
Jetson TX2 Series
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 lower-price Jetson TX2 4GB.
Jetson TX1
The world's first supercomputer on a module, Jetson TX1 delivers the performance and power efficiency needed for visual computing applications. It's built around the revolutionary NVIDIA Maxwell architecture with 256 CUDA cores delivering over 1 TFLOPs of performanceto enable embedded deep learning, computer vision, graphics, and GPU computing systems. New designs should use Jetson TX2 4GB to run neural networks with double the compute performance or double the power efficiency of Jetson TX1—at the same price.
Jetson Nano
NVIDIA Jetson Nano is a small, powerful computer for embedded AI systems and IoT that delivers the power of modern AI in a low-power platform. Get started fast with the NVIDIA Jetpack SDK and a full desktop Linux environment and start exploring a new world of embedded products.
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.
Download the latest Jetson AGX Xavier , Jetson TX2 , Jetson TX1 , and Jetson Nano hardware docs from the download center.
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.