Skip to product information
1 of 1

NVIDIA

NVIDIA 940-25160-0081-000 | IGX Thor Mini Developer Kit, T5000, 128GB, 1TB NVMe

SKU:940-25160-0081-000

1 in stock

$12,650.00 inc. GST
$11,500.00 ex. GST
Sale Sold out
Shipping calculated at checkout.

 Trade supply only. Server & GPU quote requests need a company name, ABN and work email address. We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 

20-min response

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

Custom Built Servers

Need a different spec, quantity or configuration?

We build configured-to-order refurbished servers from Cisco, Dell, HPE, NVIDIA Lenovo and Supermicro. Tell us what you need and we'll come back with options within 24 hours.

Configure your server now →

Description

The IGX Thor Developer Kit Mini is an embedded AI development platform for teams building robotics, medical imaging and industrial edge AI systems. It is built around the NVIDIA IGX T5000 module in the IGX Thor family and suits physical AI, humanoid robotics, surgical systems and real-time sensor processing at the edge.

The IGX T5000 pairs a 2560-core Blackwell GPU with 96 fifth-generation Tensor Cores and a 14-core Arm Neoverse-V3AE CPU running at up to 2.6 GHz. It delivers up to 2070 FP4 TFLOPS (sparse) from 128 GB of 256-bit LPDDR5X memory at 273 GB/s, with a 1 TB NVMe drive on an M.2 Key M PCIe Gen5 x4 slot. Networking comes from one QSFP28 cage supporting 4x 25GbE and one 5GbE RJ45 port. This Mini kit configuration carries the 128 GB and 1 TB NVMe specification for US, Canada, China, Japan and Taiwan regions.

The platform runs within a 40 W to 130 W power envelope, includes a Functional Safety Island on the SoC plus a safety MCU, and supports the NVIDIA Isaac, Metropolis and Holoscan software platforms.

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

Features

- Blackwell Multi-Instance GPU (MIG) for low-latency, real-time workloads
- Third-generation Programmable Vision Accelerator, dual encoders and decoders, and optical flow accelerator
- Functional Safety Island on the SoC plus onboard safety MCU
- Runs the NVIDIA AI Enterprise stack and NIM for physical AI, including Isaac, Metropolis and Holoscan
- Supports VLA models such as Isaac GR00T N, and LLMs and VLMs such as Cosmos Reason
- Helps accelerate medical (IEC 60601, 62304) and industrial functional safety (ISO 26262, IEC 61508) certifications
- 10-year lifecycle, built for industrial and medical environments

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

Collapsible content

Technical Specifications

FAQs

Technical Specifications

- Module: NVIDIA IGX T5000
- AI performance: Up to 2070 TFLOPS (FP4, sparse)
- GPU: 2560-core NVIDIA Blackwell architecture with 96 fifth-gen Tensor Cores
- GPU max frequency: 1.57 GHz
- Multi-Instance GPU (MIG): 10 TPCs
- CPU: 14-core Arm Neoverse-V3AE 64-bit, up to 2.6 GHz
- CPU cache: 64 KB I-Cache and 64 KB D-Cache, 1 MB L2 per core, 16 MB shared L3
- Vision accelerator: 1x PVA v3
- Memory: 128 GB 256-bit LPDDR5X, 273 GB/s
- Storage: 1 TB NVMe on M.2 Key M slot, UFS secondary storage
- Video encode: 2x NVENC
- Video decode: 2x NVDEC
- PCIe: M.2 Key M x4 PCIe Gen5, M.2 Key E x1 PCIe Gen5
- Networking: 1x QSFP28 (4x 25GbE), 1x 5GbE RJ45
- Wireless: Wi-Fi 6E and Bluetooth module
- USB: 2x USB Type-A (USB 3.2 Gen 2, 10 Gbps), 2x USB-C (5 Gbps, PD sink up to 140 W), debug USB-C
- Display: 1x DisplayPort, 1x HDMI
- Other I/O: 2x CAN headers, 2x Automation headers, 2x JTAG headers, fan connector, 2x audio panel headers, RTC battery connector
- Power input: 9-28 V DC via Micro-Fit (up to 8 A), or USB-C PD
- Power envelope: 40 W to 130 W
- Functional safety: Functional Safety Island on SoC plus safety MCU

FAQs

Q: What power does it need?
A: It operates within a 40 W to 130 W envelope. DC input is 9-28 V (up to 8 A) via Micro-Fit, and the USB-C ports act as PD sinks up to 140 W.

Q: Which software platforms does it support?
A: It supports the NVIDIA AI Enterprise stack and the Isaac, Metropolis and Holoscan platforms, including NIM for physical AI.

Q: How is the system flashed?
A: Flashing uses Linux_for_Tegra from an Ubuntu host PC over the USB-C force-recovery port.

Q: What network connections does it provide?
A: It has one QSFP28 cage supporting 4x 25GbE and one 5GbE RJ45 port, plus a Wi-Fi 6E and Bluetooth module.

Q: How does this kit differ from other IGX Thor SKUs?
A: This is the Mini configuration with the IGX T5000 module, 128 GB memory and a 1 TB NVMe drive, for the US, Canada, China, Japan and Taiwan regions.

  • 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