COR Brief
Robotics & Hardware

Jetson Thor

NVIDIA Jetson Thor is a system-on-module and developer kit designed for edge AI and robotics applications. It integrates a Blackwell GPU architecture with 2560 CUDA cores, 14 Arm Neoverse V3AE CPUs, and 128 GB of LPDDR5X memory, delivering up to 2070 FP4 TFLOPS of AI compute within a 40 to 130 watt power envelope. This performance level supports demanding generative AI models and complex robotic systems. Compared to its predecessor, the Jetson AGX Orin, Jetson Thor offers a 7.5 times increase in AI performance and 3.5 times better energy efficiency. The module supports advanced video processing capabilities, including decoding up to ten 4Kp60 streams or four 8Kp30 streams, and encoding up to six 4Kp60 streams in H.265/H.264 formats. It also supports multiple video codecs such as AV1, VP9, VP8, MPEG-2, and MPEG-4. Display output capabilities include driving up to four independent displays via HDMI 2.1 and DisplayPort 1.4a, with support for 8K resolution at 7680×4320 pixels at 30Hz. The form factor measures approximately 87 by 100 millimeters and uses a 699-pin board-to-board connector.

Updated Jan 24, 2026unknown

Jetson Thor is an NVIDIA system-on-module delivering up to 2070 FP4 TFLOPS AI compute for edge AI and robotics with enhanced video and display support.

Pricing
unknown
Category
Robotics & Hardware
Company
Interactive PresentationOpen Fullscreen ↗
01
Delivers 2070 FP4 TFLOPS AI compute powered by Blackwell GPU architecture with 2560 CUDA cores.
02
Includes 128 GB of LPDDR5X memory to support large generative AI models and complex workloads.
03
Supports decoding up to 10× 4Kp60 or 4× 8Kp30 video streams and encoding up to 6× 4Kp60 in H.265/H.264 formats, with support for AV1, VP9, VP8, MPEG-2, and MPEG-4 codecs.
04
Drives up to 4 independent displays via HDMI 2.1 and DisplayPort 1.4a, including 8K output at 7680×4320 @ 30Hz.
05
Operates within a 40–130 W power range, balancing high performance with energy efficiency.

Generative AI Model Deployment

Running large-scale generative AI models at the edge requiring high compute and memory resources.

Complex Robotics Systems

Powering humanoid robots and advanced robotics applications that demand real-time AI processing and multi-camera video input.

Multi-Camera Video Analytics

Processing multiple high-resolution video streams simultaneously for surveillance or autonomous machine vision.

1
Access Documentation and Software
Visit the NVIDIA Jetson Download Center to obtain documentation, software, tools, and drivers.
2
Set Up Developer Kit
Use the Jetson ISO image for the AGX Thor developer kit setup following the online user guide.
3
Explore Tutorials and Support
Follow tutorials and access support resources on developer.nvidia.com/embedded.
4
Connect with Jetson Partners
Engage with NVIDIA Jetson Partners for compatible products and services.
📊

Strategic Context for Jetson Thor

Get weekly analysis on market dynamics, competitive positioning, and implementation ROI frameworks with AI Intelligence briefings.

Try Intelligence Free →
7 days free · No credit card
Pricing
Model: unknown

No public pricing information is available; pricing varies by region and can be obtained via NVIDIA regional websites and partners.

Assessment
Strengths
  • Delivers up to 2070 FP4 TFLOPS AI compute within a 130 W power envelope.
  • Supports decoding of up to 10 simultaneous 4Kp60 video streams.
  • Provides 128 GB LPDDR5X memory suitable for large AI models.
  • Offers 7.5× higher AI performance compared to Jetson AGX Orin.
  • Capable of driving four independent 8K displays.
Limitations
  • Higher power consumption at 120–130 W compared to predecessor's 60 W.
  • No publicly listed pricing; requires checking regional NVIDIA sites.