NVIDIA has announced the general availability of the Jetson AGX Thor developer kit and production modules, designed for physical AI and robotics applications. Powered by NVIDIA Blackwell, Jetson Thor offers 7.5x more AI compute and 3.5x greater energy efficiency than its predecessor, Jetson Orin. Over 2 million developers are using NVIDIA's robotics stack, with early adopters including Agility Robotics, Amazon Robotics, and Boston Dynamics. Jetson Thor enables real-time reasoning inference, critical for highly performant physical AI applications.
NVIDIA has announced the general availability of the Jetson AGX Thor developer kit and production modules, designed to power physical AI and robotics applications. Powered by NVIDIA's Blackwell generation AI compute, Jetson Thor offers significant advancements in AI compute and energy efficiency compared to its predecessor, Jetson Orin.
The new kit provides 7.5x more AI compute and 3.5x greater energy efficiency [2]. This performance leap enables roboticists to process high-speed sensor data and perform visual reasoning at the edge, making it suitable for applications such as humanoid robotics and industrial automation. Early adopters include Agility Robotics, Amazon Robotics, and Boston Dynamics, which are integrating Jetson Thor into their robotic systems to enhance real-time responsiveness and complex AI skills [2].
Jetson Thor is built for generative reasoning models, supporting a wide range of AI frameworks and models, including Cosmos Reason, DeepSeek, Llama, Gemini, and Qwen [2]. Its real-time performance and low-latency capabilities make it ideal for applications that require immediate decision-making and action, such as autonomous robots navigating complex environments or smart tractors performing precision agriculture tasks.
The Jetson ecosystem supports a variety of application requirements, high-speed industrial automation protocols, and sensor interfaces, accelerating time to market for enterprise developers [2]. Hardware partners and sensor companies are leveraging Jetson Thor to build production-ready systems and elevate traditional vision AI and robotics applications.
With over 2 million developers using NVIDIA's robotics stack, Jetson Thor is set to drive innovation in physical AI and robotics, enabling real-time reasoning and inference critical for highly performant applications [2]. As the technology advances, it is expected to deliver even better throughput and faster responses with future software releases, further cementing its position as a key player in the AI and robotics market.
References:
1. [https://www.servethehome.com/nvidia-jetson-agx-thor-developer-kit-blackwell-for-robotics/](https://www.servethehome.com/nvidia-jetson-agx-thor-developer-kit-blackwell-for-robotics/)
2. [https://blogs.nvidia.com/blog/jetson-thor-physical-ai-edge/](https://blogs.nvidia.com/blog/jetson-thor-physical-ai-edge/)
Comments
No comments yet