• Black rectangular matte nvidia 940-25840-0011-000 igx thor t7000 dev kit with subtle horizontal seams
1 1

NVIDIA

NVIDIA 940-25840-0011-000 | IGX Thor Dev Kit, RTX PRO 6000 dGPU, 2x 200GbE QSFP28

940-25840-0011-000

Stock Status: Enquire

$31,878.00 inc. GST
$28,980.00 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 We do not quote Gmail, Outlook or Hotmail addresses, or supply for home use. 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 NVIDIA IGX Thor Developer Kit is an enterprise-ready edge AI development platform for industrial and medical applications. It pairs the IGX T7000 board, with its Blackwell iGPU, 14-core Arm Neoverse-V3AE CPU, BMC, ConnectX-7 SmartNIC and Safety MCU, with an NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition dGPU. It suits medical imaging, surgical and humanoid robotics, industrial AI automation and sensor processing for autonomous machines.

Together the iGPU and dGPU deliver up to 5,581 FP4-Sparse TFLOPS. The iGPU has 2,560 cores with 96 fifth-generation Tensor Cores, and the dGPU adds 24,064 cores with 96 GB of memory. The board carries 128 GB of 256-bit LPDDR5X at 273 GB/s and a 1 TB M.2 NVMe drive. Networking is 2x QSFP28 at 200GbE each, giving 400GbE in total through the ConnectX-7, plus 2x 1GbE RJ45 ports. An 850 W DC power supply is included.

The board has 2x PCIe Gen5 slots (x8 and x16), a DisplayPort 1.4a output, and USB 3.2 Gen 2 ports. It runs the NVIDIA IGX software stack, with NVIDIA AI Enterprise, Holoscan, Isaac, Metropolis and NIM supported. NVIDIA AI Enterprise-IGX is licensed separately.

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

Features

- Blackwell iGPU plus RTX PRO Blackwell dGPU for generative AI at the edge
- Transformer Engine and Multi-Instance GPU (MIG) support for workload isolation
- Functional Safety Island in the Thor SoC plus an onboard Safety MCU
- ConnectX-7 SmartNIC with 400GbE for high-speed sensor fusion
- Board Management Controller (BMC) for remote management
- Third-generation Programmable Vision Accelerator with dual encoders and decoders
- Runs NVIDIA AI Enterprise, NIM, Isaac, Metropolis and Holoscan software
- Partner ecosystem supports medical (IEC 60601, IEC 62304) and industrial safety (ISO 26262, IEC 61508) certification

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

- Platform: NVIDIA IGX T7000 board kit with BMC, ConnectX-7 SmartNIC and Safety MCU
- AI performance: up to 5,581 TFLOPS (FP4-Sparse) with RTX PRO 6000 Blackwell Max-Q
- iGPU: 2,560-core Blackwell GPU with 96 fifth-generation Tensor Cores
- iGPU maximum frequency: 1.57 GHz
- Multi-Instance GPU: 10 TPCs
- dGPU: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, 24,064 cores
- dGPU memory: 96 GB, 1,792 GB/s
- 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
- System memory: 128 GB 256-bit LPDDR5X, 273 GB/s
- Storage: 1 TB M.2 NVMe (PCIe Gen5 x2)
- Video encode: 2x NVEncode (iGPU), 4x NVEncode (dGPU)
- Video decode: 2x NVDecode (iGPU), 4x NVDecode (dGPU)
- Expansion: 2x PCIe Gen5 (x8, x16)
- Networking: 2x QSFP28 (200GbE each, 400GbE total), 2x RJ45 (1GbE each)
- Display: 1x DisplayPort 1.4a
- USB: 4x USB 3.2 Gen 2 Type-A, 1x USB 3.2 Gen 2 Type-C
- Other I/O: 1x FSI CAN, audio line-out, MIC in
- Power: 40 W to 130 W TMP, up to 300 W for the dGPU, 850 W DC power supply
- Dimensions: 262.70 mm x 382.70 mm x 151.20 mm

FAQs

Q: Does it need a software licence?
A: NVIDIA AI Enterprise software is supported on the kit. NVIDIA AI Enterprise-IGX is licensed separately, so check NVIDIA's AI Enterprise-IGX licensing guide for the tier you need.

Q: What power supply does it use?
A: It runs from an 850 W DC power supply. The module envelope is 40 W to 130 W TMP, with up to 300 W available for the RTX PRO 6000 Blackwell Max-Q dGPU.

Q: What expansion does the board offer?
A: The board has 2x PCIe Gen5 slots (x8 and x16) and supports RTX PRO Blackwell dGPUs. The M.2 Key-M slot holds the 1 TB NVMe drive.

Q: How fast is the networking?
A: The ConnectX-7 SmartNIC provides 2x QSFP28 ports at up to 200GbE each, for 400GbE in total, alongside 2x 1GbE RJ45 ports.

Q: Which software stacks does it run?
A: It supports the NVIDIA IGX software stack, NVIDIA AI Enterprise, Holoscan, Isaac, Metropolis, NIM and Halos.

Related Products

View all Enterprise Servers: Rack, Tower & Blade

  • 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