• Placeholder image
1 0

NVIDIA

NVIDIA 900-13834-0000-0A1 | Jetson Thor T4000 AI Module, 1200 TFLOPS, 64GB, 12-Core

900-13834-0000-0A1

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 T4000 is a compact system-on-module designed for edge AI, robotics, and physical AI applications. Built on the Blackwell GPU architecture, it delivers up to 1200 FP4 TFLOPS of AI compute performance with 64GB LPDDR5X memory and a 12-core Arm Neoverse-V3AE CPU. Configurable power envelope from 40W to 70W enables flexible deployment across autonomous robots, industrial automation, smart infrastructure, and real-time multi-sensor AI workloads.

Features

NVIDIA Blackwell GPU architecture with transformer engine for generative AI models
- Multi-Instance GPU (MIG) support for workload isolation and resource partitioning
- 12-core Arm Neoverse-V3AE CPU with low-latency real-time processing capabilities
- 64GB LPDDR5X memory with 273.2 GB/s bandwidth for intensive vision and multimodal AI
- Triple 25 GbE networking for high-speed sensor data ingestion and edge connectivity
- Hardware video codec engines: 1x NVENC and 1x NVDEC for real-time 4K video processing
- 3rd-generation Programmable Vision Accelerator (PVA) for computer vision acceleration
- Optical flow accelerator for motion estimation and tracking applications
- Configurable power profile from 40W to 70W for thermal optimization
- Pin-compatible with Jetson T5000 for flexible product scaling
- Support for Vision-Language-Action (VLA) models including NVIDIA Isaac GR00T
- Compatible with LLMs, VLMs, and multimodal generative AI frameworks
- CUDA 11.4+, OpenGL 4.6+, OpenGL ES 3.2, Vulkan 1.1+ graphics API support
- End-to-end lossless compression and tile caching for memory efficiency
- Comprehensive safety and security mechanisms for industrial deployment

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

AI Compute Performance: Up to 1200 FP4 TFLOPS (sparse)
- GPU: NVIDIA Blackwell architecture, 1536 CUDA cores, 64 Tensor cores (5th generation)
- CPU: 12-core Arm Neoverse-V3AE (64-bit)
- System Memory: 64GB LPDDR5X, 256-bit interface, 273.2 GB/s bandwidth
- Power Consumption: Configurable 40W to 70W TDP
- Networking: 3x 25 GbE connectivity
- Video Codec: 1x NVENC encoder, 1x NVDEC decoder, real-time 4K encode/decode
- Accelerators: 3rd-generation Programmable Vision Accelerator (PVA), optical flow accelerator
- Cache: 50MB L2 cache
- Form Factor: Compact SOM, 243mm length, pin-compatible with Jetson T5000
- Manufacturing Process: TSMC 3nm
- Architecture: NVIDIA Blackwell with Multi-Instance GPU (MIG) support

FAQs

Q: What applications is the Jetson T4000 designed for?
A: The Jetson T4000 is optimized for physical AI and robotics applications including autonomous mobile robots, humanoid robotics, industrial automation, smart infrastructure, and edge AI deployments requiring real-time multi-sensor processing and generative AI inference.

Q: How does the T4000 compare to the AGX Orin module?
A: The Jetson T4000 delivers over 4x the AI compute performance compared to the Jetson AGX Orin while maintaining exceptional energy efficiency. It provides 1200 FP4 TFLOPS versus approximately 275 TOPS on AGX Orin, with a newer Blackwell GPU architecture and transformer engine support.

Q: Is the T4000 pin-compatible with other Jetson Thor modules?
A: Yes, the Jetson T4000 shares the same form factor and pin compatibility with the Jetson T5000 module, allowing developers to design common carrier boards that support both modules while accounting for differences in thermal requirements and power profiles.

Q: What software frameworks are supported?
A: The T4000 runs NVIDIA JetPack and supports the complete NVIDIA AI software stack including NVIDIA Isaac for robotics, Metropolis for visual AI, Holoscan for sensor processing, TensorRT for inference optimization, and popular AI frameworks for LLMs, VLMs, and Vision-Language-Action models.

Q: Does the module require a carrier board?
A: Yes, the Jetson T4000 is a system-on-module that requires a carrier board for deployment. NVIDIA and ecosystem partners offer reference carrier boards, or customers can design custom carrier boards for application-specific I/O, networking, and peripheral requirements.

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