• Black circuit board of nvidia igx t5000 ai module with central green to yellow gradient sensor and metallic black components
1 1

NVIDIA

NVIDIA 900-13834-0000-000 | Jetson Thor T4000 AI Module, 1200 TFLOPS, 64GB, 40-70W

900-13834-0000-000

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 Jetson Thor T4000 is a compact Blackwell-based system-on-module built for robotics and physical AI. It suits humanoid robots, real-time multi-sensor and camera applications, and edge AI deployments that need serious on-device compute. NVIDIA positions it as offering over 4x the AI compute of Jetson AGX Orin.

This 64GB variant delivers up to 1200 FP4 TFLOPS (sparse) from a 1536-core Blackwell GPU with 64 fifth-generation Tensor Cores and Multi-Instance GPU support. A 12-core Arm Neoverse-V3AE CPU runs at up to 2.6 GHz, backed by 64 GB of 256-bit LPDDR5X memory at 273 GB/s. Power is configurable between 40 W and 70 W, and networking is handled by 3x up to 25 GbE.

The module connects to a carrier board through a 699-pin B2B connector in a 100 mm x 87 mm footprint, with an integrated thermal transfer plate and heat pipe. It supports NVMe storage over PCIe, USB 3.2 SSDs and runs NVIDIA Jetson Linux. No separate licence is needed for the module itself.

Enquire with XS Network Tech for new or used pricing and availability.

Features

- Over 4x the AI compute of Jetson AGX Orin with high energy efficiency
- Blackwell GPU with fifth-generation Tensor Cores and Multi-Instance GPU
- 12-core Arm Neoverse-V3AE CPU for real-time multi-sensor processing
- 3x 25 GbE networking and extensive I/O for sensor fusion
- Supports the NVIDIA Isaac platform and GR00T foundation models for humanoid robotics and physical AI
- End-to-end security and safety across the compute stack
- Integrated thermal transfer plate with heat pipe

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 performance: up to 1200 TFLOPS (FP4 sparse), 600 FP8 TFLOPS
- GPU: 1536-core NVIDIA Blackwell architecture with 64 fifth-generation Tensor Cores
- Multi-Instance GPU: yes, 6 TPCs
- GPU maximum frequency: 1.57 GHz
- CPU: 12-core Arm Neoverse-V3AE 64-bit, up to 2.6 GHz
- CPU cache: 64 KB I-cache, 64 KB D-cache, 1 MB L2 per core, 16 MB shared system L3
- Vision accelerator: 1x PVA v3
- Memory: 64 GB 256-bit LPDDR5X, 273 GB/s peak bandwidth, up to 4266 MHz
- Storage: NVMe via PCIe, SSD via USB 3.2
- Video encode: 1x NVENC (preliminary)
- Video decode: 1x NVDEC (preliminary)
- Camera: C-PHY 2.1 and D-PHY 2.1, up to 20 cameras via HSB
- PCIe: up to 8 lanes Gen5
- USB: 3x USB 3.2, 4x USB 2.0
- Networking: 3x up to 25 GbE (MGBE)
- Display: 4x shared HDMI 2.1, DisplayPort 1.4a HBR2 with MST
- Other I/O: 13x I2C, 2x DMIC, 3x SPI, 4x CAN, 4x UART, 5x I2S, 6x PWM
- Power: 40 W to 70 W configurable
- Mechanical: 100 mm x 87 mm, 699-pin B2B connector, integrated thermal transfer plate with heat pipe
- Security: 128-bit AES encryption, TrustZone secure and OS-protection regions
- Operating system: NVIDIA Jetson Linux

FAQs

Q: Does the Jetson Thor T4000 need a software licence?
A: No separate licence is needed for the module. It runs NVIDIA Jetson Linux with the JetPack SDK.

Q: What power does it need?
A: The module has a configurable power profile of 40 W to 70 W, so you can balance performance against your thermal and power budget.

Q: How does it connect to my system?
A: It mounts on a carrier board through a 699-pin B2B connector. It supports NVMe storage over PCIe and SSD storage over USB 3.2.

Q: How does the T4000 differ from the Jetson T5000?
A: The T4000 is the lower-tier sibling. It offers 1200 FP4 TFLOPS, 64 GB of memory and a 12-core CPU, while the T5000 offers 2070 FP4 TFLOPS, 128 GB and a 14-core CPU.

Q: What applications is it designed for?
A: It targets robotics, humanoid robots, physical AI and real-time multi-sensor or camera applications at the edge.

Related Products

View all Graphics Card | GPU

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