1 1

NVIDIA

NVIDIA 900-13834-0080-000 | Jetson Thor T5000 AI Module, 2070 TFLOPS, 128GB

900-13834-0080-000

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 T5000 is a production system-on-module from the NVIDIA Jetson Thor series, built for humanoid robotics and physical AI. It is aimed at developers and OEMs building autonomous machines, agentic AI at the edge, and systems that run generative AI models such as VLAs, LLMs and VLMs locally.

At its core is a 2560-core Blackwell GPU with 96 fifth-generation Tensor Cores, delivering up to 2070 FP4 TFLOPS (sparse). It is paired with a 14-core Arm Neoverse-V3AE CPU running up to 2.6 GHz and 128 GB of 256-bit LPDDR5X memory with 273 GB/s of bandwidth. Networking is handled by 4x 25 GbE, and the module supports up to 20 cameras via the Holoscan Sensor Bridge. Module power is configurable between 40 W and 130 W. NVIDIA positions it at over 7.5x the AI compute of Jetson AGX Orin with 3.5x better energy efficiency.

The module uses a 699-pin board-to-board connector and an integrated thermal transfer plate with heatpipe, and measures 100 mm x 87 mm. It requires a Jetson Thor-compatible carrier board, with the Jetson AGX Thor Developer Kit as the reference platform, plus a matching thermal solution. It is supported by the NVIDIA Jetson Linux and JetPack software stack, the Isaac platform and GR00T foundation models.

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

Features

- Blackwell GPU with Transformer Engine and Multi-Instance GPU (MIG) support for generative AI models at the edge
- Over 7.5x the AI compute of Jetson AGX Orin with 3.5x better energy efficiency
- Runs generative AI models including VLAs, LLMs and VLMs
- 4x 25 GbE networking, camera offload engine and Holoscan Sensor Bridge support for high-speed sensor processing
- Supported by the NVIDIA Isaac platform and GR00T foundation models for humanoid robotics
- Integrated thermal transfer plate with heatpipe in a compact module footprint

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: 2070 TFLOPS (FP4, sparse)
- GPU: 2560-core NVIDIA Blackwell architecture with 96 fifth-gen Tensor Cores
- GPU Multi-Instance GPU (MIG): 10 TPCs
- GPU maximum frequency: 1.57 GHz
- CPU: 14-core Arm Neoverse-V3AE 64-bit, 1 MB L2 cache per core, 16 MB shared system L3 cache
- CPU maximum frequency: 2.6 GHz
- Vision accelerator: 1x PVA v3
- Memory: 128 GB 256-bit LPDDR5X, 273 GB/s
- Storage: NVMe through PCIe, SSD through USB 3.2
- Video encode: 6x 4Kp60, 12x 4Kp30, 24x 1080p60, 50x 1080p30 (H.265)
- Video decode: 4x 8Kp30, 10x 4Kp60, 22x 4Kp30, 46x 1080p60, 92x 1080p30 (H.265)
- Camera: up to 20 cameras via HSB, up to 6 cameras through 16 lanes MIPI CSI-2, up to 32 using virtual channels
- Camera interface: C-PHY 2.1 (10.25 Gbps), D-PHY 2.1 (40 Gbps)
- PCIe: up to Gen5 (x8 lanes)
- USB: 3x USB 3.2, 4x USB 2.0
- Networking: 4x 25 GbE
- Display: 4x shared HDMI 2.1, VESA DisplayPort 1.4a (HBR3, MST)
- Other I/O: 5x I2S/2x AHUB, 2x DMIC, 4x UART, 4x CAN, 3x SPI, 13x I2C, 6x PWM outputs
- Power: 40 W to 130 W configurable
- Dimensions: 100 mm x 87 mm
- Connector: 699-pin B2B connector with integrated Thermal Transfer Plate and heatpipe

FAQs

Q: Does the Jetson Thor T5000 need a software licence?
A: No separate licence has been identified for the module. It is supported by the NVIDIA Jetson Linux and JetPack software stack.

Q: What power does the module need?
A: Module power is configurable from 40 W to 130 W. Power is delivered through the carrier board via the 699-pin B2B connector.

Q: What does it need to work?
A: It requires a Jetson Thor-compatible carrier board, with the Jetson AGX Thor Developer Kit as the reference platform. It also needs a matching thermal solution such as a fan or heat sink.

Q: Can it connect to cameras and sensors?
A: Yes. It supports up to 20 cameras via the Holoscan Sensor Bridge, plus MIPI CSI-2 camera inputs.

Q: What AI workloads is it designed for?
A: It is built for humanoid robots and physical AI, agentic AI at the edge, large transformer models and real-time multi-sensor processing.

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