NVIDIA is pushing more AI power into a smaller robotics package. On Aug. 25, 2026, at 11:00 AM, the company announced the Jetson Orin Nano 2, an entry-level edge AI robotics computer expected to arrive in the first half of 2027.
The headline is simple: Jetson Orin Nano 2 delivers twice the inference performance of its predecessor in the same form factor, while using 40% less power at the same performance. That combination gives developers a more capable computer without changing the compact design or accepting higher power use.
Twice the Inference Performance in the Same Form Factor
Jetson Orin Nano 2 brings 78 trillion operations per second of AI compute, 8GB of memory, and an 8-core Arm CPU. Those specifications target robotics systems that need to process AI workloads at the edge, where inference performance and power consumption directly shape what a device can do.
NVIDIA says the new computer achieves twice the inference performance of the Jetson Orin Nano Super. The gain comes from improved Tensor Cores and higher memory bandwidth, two upgrades that help the system handle AI inference workloads with greater capacity than the earlier product.
The performance increase matters because edge devices must operate within the limits of their physical hardware. Jetson Orin Nano 2 keeps the same form factor as its predecessor, so the new performance level arrives in a package designed for entry-level edge AI robotics computers.
- 78 trillion operations per second of AI compute
- 8GB of memory
- 8-core Arm CPU
- 2x the inference performance of Jetson Orin Nano Super
- 40% less power in 15-watt mode at the same performance as its predecessor
More AI Capability Without More Power
Power efficiency gives Jetson Orin Nano 2 another clear advantage. In 15-watt mode, it consumes 40% less power while delivering the same performance as its predecessor, creating a stronger balance between computing power and energy use.
That balance is central to edge AI. The computer must provide enough processing power for real-time intelligence, but it also needs to stay within a defined power target. Jetson Orin Nano 2 addresses both sides of that challenge by pairing twice the inference performance with a 40% reduction in power at the same performance level.
Deepu Talla, vice president of robotics and edge AI at NVIDIA, connected the new hardware to a shift in AI model capability: “Today’s small and medium frontier models have reached the accuracy of last year’s largest frontier models, unlocking real-time intelligence for edge devices.”
That statement points to the role Jetson Orin Nano 2 is designed to play. The computer brings AI compute directly to edge devices, where smaller and medium frontier models can support real-time intelligence without relying on a larger computer in the same location.
A Platform for Robotics, Drones, and Home Machines
More than 3 million developers have built on the NVIDIA robotics stack, giving the Jetson Orin Nano 2 a large developer community around the platform. The new module and developer kit are expected to be available in the first half of 2027, opening a path for developers to build with the updated hardware.
The announcement also names Cognex, Doosan Bobcat, Matic, and Wing. Wing is a drone delivery company and subsidiary of Alphabet, and Dinuka Abeywardena described the role of edge AI in that field: “Drone delivery depends on AI that can enable fast, reliable understanding of the real world.”
That demand fits the Jetson Orin Nano 2 profile. A drone delivery system needs AI compute inside an edge device, and the new computer combines 78 trillion operations per second with an 8-core Arm CPU and 8GB of memory.
Matic also brings the home robotics perspective into focus. Navneet Dalal, cofounder and CEO of Matic Robotics, said: “Home robots need to understand people, map spaces precisely, understand the layout of objects and spaces, and clean autonomously in dynamic and constantly changing environments.”
Those tasks require a robot to interpret its surroundings and act on that understanding. Jetson Orin Nano 2 is built for entry-level edge AI, but its improved Tensor Cores, higher memory bandwidth, and twice the inference performance of Jetson Orin Nano Super give developers a stronger hardware base for robotics computers.
The next milestone is availability. NVIDIA expects the Jetson Orin Nano 2 module and developer kit in the first half of 2027, bringing its performance and power improvements to the developers building the next generation of edge AI robotics systems.
Based on
