Experience the world's most powerful AI computer in a small Jetson form factor, built for energy-efficient autonomous machines. Compared to the previous generation, it offers 5x the performance and twice the number of CUDA cores, as well as high-speed interface support for multiple sensors. Jetson Orin NX has 100 TOPS of computing power for multiple concurrent AI inference pipelines in a compact form factor with outstanding performance。
Measuring just 70mm x 45mm, Jetson Orin™ NX delivers 5x the performance of NVIDIA Jetson Xavier™ NX. Small size, high performance, and high energy efficiency bring superior performance to next-generation products such as drones and handheld devices。
NVIDIA Jetson Orin NX features NVIDIA Ampere architecture GPU and Arm® Cortex®-A78AE CPU, as well as next-generation deep learning and vision accelerators. High-speed IO, 102GB/s memory bandwidth, and 12GB DRAM capable of feeding multiple concurrent AI application pipelines。
Experience the increased performance of small form factor robots and autonomous machines in a compact, energy efficient system. The power consumption of the compact module is only 10 watts and can be capped at 25 watts. Gain insight into Jetson Orin NX's disruptive size, performance and power consumption, as well as the NVIDIA JetPack™ SDK, NVIDIA AI software stack and ecosystem of services and products to get your products to market fast。
Jetson Orin NX 8GB | Jetson Orin NX 16GB | |
| AI 性(xìng)能(néng) | 70 TOPS | 100 TOPS |
| GPU | 搭载(zài) 32 个(gè) Tensor Core 的(de) 1024 核 NVIDIA Ampere 架構 GPU | |
| GPU 最(zuì)大(dà)頻率 | 765 MHz | 918 MHz |
| CPU | 6 核 Arm® Cortex®-A78AE v8.2 64 位(wèi) CPU 1.5MB L2 + 4MB L3 | 8 核 Arm® Cortex®-A78AE v8.2 64 位(wèi) CPU 2MB L2 + 4MB L3 |
| CPU 最(zuì)大(dà)頻率 | 2 GHz | |
| DL 加速器 | 1x NVDLA v2 | 2x NVDLA v2 |
| DLA 最(zuì)大(dà)頻率 | 614 MHz | |
| 视覺加速器 | 1x PVA v2 | |
| 安(ān)全(quán)集群(qún)引擎 | - | |
| 显存 | 8GB 128 位(wèi) LPDDR5 102.4GB/s | 16GB 128 位(wèi) LPDDR5 102.4GB/s |
| 存儲 | (支持(chí)外(wài)部(bù) NVMe) | |
| 视頻編碼 | 1x 4K60 (H.265) 3x 4K30 (H.265) 6x 1080p60 (H.265) 12x 1080p30 (H.265) | |
| 视頻解(jiě)碼 | 1x 8K30 (H.265) 2x 4K60 (H.265) 4x 4K30 (H.265) 9x 1080p60 (H.265) 18x 1080p30 (H.265) | |
| 攝像头(tóu) | 最(zuì)多(duō) 4 个(gè)攝像头(tóu)(通(tòng)过(guò)虛拟通(tòng)道最(zuì)多(duō)可(kě)支持(chí) 8 个(gè)***) 8 通(tòng)道 MIPI CSI-2 D-PHY 2.1(高(gāo)达(dá) 20 Gbps) | |
| PCIe* | 1 x4 + 3 x1 (PCIe 4.0,根(gēn)端口和(hé)端點(diǎn)) | |
| USB* | 3x USB 3.2 2.0 (10 Gbps) 3x USB 2.0 | |
| 网(wǎng)络* | 1x GbE | |
| 显示接口 | 1x 8K30 多(duō)模 DP 1.4a (+MST)/eDP 1.4a/HDMI 2.1 | |
| 其(qí)他(tā) I/O | 3x UART、2x SPI、2x I2S、4x I2C、1x CAN、DMIC 和(hé) DSPK、PWM、GPIO | |
| 功耗 | 10 瓦(wǎ)至(zhì) 20 瓦(wǎ) | 10 瓦(wǎ)至(zhì) 25 瓦(wǎ) |
| 規格尺(chǐ)寸 | 69.6mm x 45mm 260 引脚 SO-DIMM 連(lián)接器 | |
The NVIDIA JetPack SDK provides access to all Jetson hardware capabilities and allows developers to apply the world-class NVIDIA AI software stack to their next...
Many AI applications face common needs: classification, object detection, language translation, text-to-speech, recommender system engines, sentiment analysis, ...
NVIDIA software platforms including Isaac™ for robotics, Clara™ for healthcare, and Metropolis for smart cities accelerate vertical-specific applications。
Robots create new efficiencies and improve quality of life in industries such as manufacturing, logistics, healthcare and services. NVIDIA Isaac accelerates thi...
NVIDIA Clara is a healthcare application framework for the development and deployment of AI-powered imaging, genomics, and smart sensors. It includes full-stack...
NVIDIA Metropolis includes an application framework, a set of developer tools, and an ecosystem of partners that combine visual data and AI to improve operation...