The option marked with * is required. After submission, our company will arrange a business email to send you the corresponding product PDF document

Product features

Product function

Block diagram of Jetson Orin Nano including up to 1024 Core NVIDIA Ampere Architecture GPU, 6 core Arm Cortex-A78AE CPU, 4 or 8 GB of memory, NVDec, ISP, Video Image Compositor, APE, Power Subsystem, and various interfaces including seven lanes of PCIe Gen3, 3x USB 3.2 Gen2, 3x USB, I2C, QSPI, CAN, GPIO, UART, I2S, and PWM.

* NVIDIA Orin architecture of Jetson Orin Nano 8GB. Jetson Orin Nano 4GB has 2 TPC and 4 SM. 

As shown in figure 1, Jetson Orin Nano shows the NVIDIA-Orin architecture with NVIDIA ampere architecture GPU. 

It has up to 8 streaming multiprocessors (SM) and consists of 1024 CUDA cores and up to 32 tensor cores for AI processing. 

The third-generation Tensor Cores of NVIDIA Ampere Architecture outperforms the previous generation in performance per watt and brings higher performance while supporting sparsity. 

With sparsity, you can double the throughput of Tensor Core operations by taking advantage of the fine-grained structured sparsity in deep learning networks. 

To speed up all parts of the application pipeline, Jetson Orin Nano also includes a 6-core Arm Cortex-A78AE CPU, video decoding engine, ISP, video image synthesizer, audio processing engine, and video input block. 

Jetson Orin Nano module covers a small area, for 70x45mm, 260-pin SODIMM, including a variety of high-speed interfaces:

  • Up to seven PCIe Gen3 channels. 

  • Three high-speed 10 Gbps USB 3.2 Gen2 ports. 

  • Eight-channel MIPI CSI-2 camera port. 

  • Various sensor I / O

In order to reduce your engineering workload, we have made Jetson Orin Nano and Jetson Orin NX modules fully compatible with pins and shapes. 

Table 1 shows the differences between Jetson Orin Nano 4GB and Jetson Orin Nano 8GB.

Jetson Orin Nano 4GBJetson Orin Nano 8GB
AI 性能20 Sparse TOPs | 10 Dense TOPs40 Sparse TOPs | 20 Dense TOPs
GPU512-core NVIDIA Ampere Architecture GPU with 16 Tensor Cores1024-core NVIDIA Ampere Architecture GPU with 32 Tensor Cores
GPU 最大频率625 MHz
CPU6-core Arm Cortex-A78AE v8.2 64-bit CPU 1.5 MB L2 + 4 MB L3
CPU 最大频率y1.5 GHz
内存4GB 64-bit LPDDR5 34 GB/s8GB 128-bit LPDDR5 68 GB/s
(Supports external NVMe)
视频加码1080p30 supported by 1-2 CPU cores
视频解码1x 4K60 (H.265) | 2x 4K30 (H.265) | 5x 1080p60 (H.265) | 11x 1080p30 (H.265)
摄像头Up to 4 cameras (8 through virtual channels*) 8 lanes MIPI CSI-2 D-PHY 2.1 (up to 20 Gbps)
PCIe1 x4 + 3 x1 (PCIe Gen3, Root Port, & Endpoint)
USB3x USB 3.2 Gen2 (10 Gbps) 3x USB 2.0
网络1x GbE
Display1x 4K30 multimode DisplayPort 1.2 (+MST)/e DisplayPort 1.4/HDMI 1.4*
其他 I/O3x UART, 2x SPI, 2x I2S, 4x I2C, 1x CAN, DMIC and DSPK, PWM, GPIOs
电量5W – 10W7W – 15W
机械69.6 mm x 45 mm 260-pin SO-DIMM connector

Online consultation