Jetson Orin Nano
An entry-level edge computing module in NVIDIA's Jetson series. It integrates GPU compute capability and supports low-power offline AI inference, and is widely deployed in edge AI applications such as autonomous robots, drone navigation, and industrial machine vision inspection.
Timeline (last 90 days)
On Jetson AGX Thor, d1-3B takes 16 milliseconds to answer one question and 20 milliseconds for three questions; on Jetson AGX Orin 64GB it is 26 milliseconds and 35 milliseconds; on Jetson Orin Nano it is 50 milliseconds and 73 milliseconds.
Projected data for Redwood on Samsung's 8nm process shows inference throughput 1.75× that of the measured Jetson Orin Nano.
Redwood reduces power consumption by 1.9× compared to the Jetson Orin Nano and improves performance per watt by 3.4× (based on projected data).
The Jetson Orin Nano (8GB version) consumes only 15W of power and can run quantized 2B models smoothly.
The Jetson Orin Nano uses the Ampere architecture, with a rated performance of 20–40 TOPS (INT8) and a price of approximately $250–$500.
All Facts (5)
The Jetson Orin Nano (8GB version) consumes only 15W of power and can run quantized 2B models smoothly.
60%UnverifiedOn Jetson AGX Thor, d1-3B takes 16 milliseconds to answer one question and 20 milliseconds for three questions; on Jetson AGX Orin 64GB it is 26 milliseconds and 35 milliseconds; on Jetson Orin Nano it is 50 milliseconds and 73 milliseconds.
50%UnverifiedProjected data for Redwood on Samsung's 8nm process shows inference throughput 1.75× that of the measured Jetson Orin Nano.
50%UnverifiedRedwood reduces power consumption by 1.9× compared to the Jetson Orin Nano and improves performance per watt by 3.4× (based on projected data).
50%UnverifiedThe Jetson Orin Nano uses the Ampere architecture, with a rated performance of 20–40 TOPS (INT8) and a price of approximately $250–$500.
50%