• Placeholder image
1 0

NVIDIA

NVIDIA 900-13834-0080-0A1 | Jetson Thor AI Module, 2070 TOPS, Blackwell GPU, 128GB

900-13834-0080-0A1

Stock Status: Enquire

Request Quote
Sale Sold out
Shipping calculated at checkout.
20-min response

Need a quote or bulk pricing? Answered within 20 minutes, Sydney business hours.

Description

The NVIDIA Jetson T5000 is a high-performance system-on-module designed for physical AI, robotics, and edge AI applications. Built on the Blackwell GPU architecture with 2560 CUDA cores and 96 fifth-generation Tensor Cores, it delivers up to 2070 FP4 TFLOPS of AI compute performance with 128GB LPDDR5X memory. The module features a 14-core ARM Neoverse V3AE CPU, 4x 25GbE networking, and extensive I/O including PCIe Gen5 support, making it ideal for autonomous systems, humanoid robotics, and real-time multi-sensor fusion applications.

Features

NVIDIA Blackwell GPU architecture with 2560 CUDA cores and 96 fifth-generation Tensor Cores
- Multi-Instance GPU (MIG) support for workload isolation and multi-tenancy
- Transformer Engine for accelerated generative AI model inference
- Third-generation Programmable Vision Accelerator (PVA v3.0) for efficient computer vision processing
- 14-core ARM Neoverse V3AE CPU delivering 2.6x performance improvement over previous generation
- 128GB LPDDR5X high-bandwidth memory with 273GB/s throughput
- Quad 25 Gigabit Ethernet interfaces for high-speed sensor and network connectivity
- PCIe Gen5 support with 12 lanes at 32GT/s per lane for maximum I/O bandwidth
- Dual video encoders and decoders with 8K video capability
- Optical flow accelerator for motion analysis and tracking applications
- Holoscan Sensor Bridge for camera offload engine and real-time sensor processing
- Configurable power from 40W to 130W for flexible thermal design
- Compatible with NVIDIA Isaac robotics platform, Metropolis visual AI, and Holoscan sensor frameworks
- Support for Vision Language Action (VLA), Large Language Model (LLM), and Vision Language Model (VLM) inference
- Standard 100mm x 87mm form factor compatible with Jetson AGX ecosystem

Warranty

All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability.

All technical data should be verified on the manufacturer data sheets.

View full details

specs-tabs

Technical Specifications

FAQs

Technical Specifications

GPU: NVIDIA Blackwell architecture with 2560 CUDA cores, 96 Tensor Cores
- AI Performance: Up to 2070 FP4 TFLOPS (sparse), 7.8 FP32 TFLOPS
- CPU: 14-core ARM Neoverse V3AE at 2.6GHz
- Memory: 128GB LPDDR5X 256-bit with 273GB/s bandwidth
- Power: Configurable 40W to 130W TDP
- Networking: 4x 25GbE, 1x 5GbE
- PCIe: 12 lanes Gen5 (32GT/s per lane)
- USB: 3x USB 3.2 ports
- Storage: Supports NVMe SSD (1TB on reference carrier)
- Video: Dual encoders/decoders, 8K video support
- AI Accelerators: Third-generation Programmable Vision Accelerator (PVA v3.0), optical flow accelerator
- Form Factor: 100mm x 87mm system-on-module
- Weight: Approximately 280g (module only)
- Management: Multi-Instance GPU (MIG) support, Transformer Engine

FAQs

Q: What applications is the Jetson T5000 designed for?
A: The Jetson T5000 is purpose-built for physical AI and robotics applications including autonomous mobile robots, humanoid robotics, industrial automation, warehouse logistics, and advanced computer vision systems. It excels at running generative AI models like Vision Language Action (VLA) models, large language models (LLMs), and vision language models (VLMs) at the edge with real-time multi-sensor fusion capabilities.

Q: How does the T5000 compare to previous Jetson modules?
A: The Jetson T5000 delivers over 7.5x higher AI compute performance compared to the Jetson AGX Orin, with 3.5x better energy efficiency. It features the latest Blackwell GPU architecture versus Orin's Ampere architecture, a more powerful 14-core Neoverse V3AE CPU, double the memory at 128GB, and advanced networking with 4x 25GbE interfaces plus PCIe Gen5 support for next-generation peripherals.

Q: Does the T5000 require a carrier board?
A: Yes, the Jetson T5000 is a system-on-module (SoM) that requires a carrier board for deployment. NVIDIA offers the Jetson AGX Thor Developer Kit with a reference carrier board featuring WiFi 6E, NVMe storage, and comprehensive I/O. Third-party partners also provide custom carrier boards for specific industrial, robotics, and embedded applications.

Q: What AI frameworks and software does the T5000 support?
A: The Jetson T5000 runs the NVIDIA AI software stack including NVIDIA Isaac for robotics, NVIDIA Metropolis for visual AI, and NVIDIA Holoscan for sensor processing. It supports popular deep learning frameworks like TensorFlow, PyTorch, and ONNX Runtime, with optimized libraries for computer vision, natural language processing, and agentic AI workflows at the edge.

Q: What connectivity options does the T5000 provide?
A: The T5000 offers extensive connectivity including 4x 25 Gigabit Ethernet and 1x 5 Gigabit Ethernet for high-speed networking, 12 lanes of PCIe Gen5 for expansion cards and storage, 3x USB 3.2 ports, multiple UART, SPI, and I2C interfaces for sensors and peripherals, and support for multiple high-resolution camera inputs through the Holoscan Sensor Bridge.

Recently Viewed

  • Request a Quote

    Looking for competitive pricing? Submit a request, and our team will provide a tailored quote that fits your needs.

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Call us Now  

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Contact us