- Semiconductor BusinessHOME
- Products and Services of Macnica,Inc.
-
technical information
-
Events and Seminars
- Handling Manufacturer
- Support
- Inquiry
- Click here to purchase products
- Semiconductor business e-mail magazine registration
Product Summary
NVIDIA IGX Thor™ is a robotics platform for industrial and medical edge applications, providing real-time sensor processing and AI inference, along with industrial-grade hardware, enterprise software, and long-term support, delivering the performance, durability, security, and safety to power autonomous robots and physical AI agents at the edge.
This is a new class of enterprise edge and robotic computers purpose-built to power next-generation industrial and medical edge applications. Leveraging the NVIDIA Blackwell GPU architecture, it excels at generative inference and multimodal sensor processing, supporting a wide range of generative AI models, from Vision Language Action (VLA) models like the NVIDIA Isaac™ GR00T N to popular LLM and VLM models like the NVIDIA Cosmos™ Reason. It also runs the NVIDIA AI Enterprise software stack and NVIDIA NIM™ for physical AI applications, delivering a seamless cloud-to-edge experience. This includes NVIDIA Isaac for robotics, NVIDIA Metropolis for visual AI agents, and NVIDIA Holoscan for sensor processing. Industrial safety AI agents can also be deployed to the edge using the NVIDIA Halos Outside-in Safety Agent Blueprint.
NVIDIA IGX T5000 Module / NVIDIA IGX T7000 Board Kit
The NVIDIA IGX Thor™ platform combines industrial-grade hardware, enterprise software, and functional safety to enable real-time sensor processing and AI inference for physical AI agents and robots. Equipped with an NVIDIA Blackwell architecture iGPU and optional dGPU, it easily runs multiple generative AI models at the edge with up to 5581 TFLOPS of AI computing performance. The NVIDIA IGX Thor platform is available in two systems: the NVIDIA IGX T5000 module and the NVIDIA IGX T7000 board kit.
NVIDIA IGX Thor Developer Kit
The NVIDIA IGX Thor Developer Kit uses the IGX T7000 board with an NVIDIA Blackwell architecture iGPU, including a 14-core Arm® Neoverse®-V3AE CPU, a board management controller (BMC), and an NVIDIA ConnectX™-7 SmartNIC. It can also be expanded with an NVIDIA RTX PRO™ Blackwell dGPU, providing up to 5,581 FP4 TFLOPS of AI computing power and 400 GbE high-speed connectivity.
The NVIDIA IGX Thor Developer Kit Mini includes an IGX T5000 module, reference board, heatsink, and extensive I/O options. Featuring an advanced NVIDIA Blackwell architecture GPU and 128 GB of memory, it easily runs the latest generative AI models and delivers up to 2070 FP4 TFLOPS of AI computing power.
Product Specifications
NVIDIA IGX T5000 Module / NVIDIA IGX T7000 Board Kit Specification Table
|
|
NVIDIA IGX T5000 |
NVIDIA IGX T7000 |
|
|
dGPU options |
- |
With NVIDIA RTX Pro 6000 Blackwell Max-Q Workstation Edition |
With NVIDIA RTX Pro Blackwell 5000 |
|
AI performance |
2,070 TFLOPS (FP4-Sparse) |
Up to 5,581 TFLOPS (FP4-Sparse) |
Up to 4,293 TFLOPS (FP4-Sparse) |
|
iGPU |
2,560-core NVIDIA Blackwell architecture GPU with 96 fifthgeneration Tensor Cores Multi- nstance GPU with 10 TPCs |
||
|
iGPU maximum frequency |
1.57 GHz |
||
|
dGPU |
- |
24,064-core Blackwell architecture GPU with fifth-generation Tensor Cores |
14,080-core Blackwell architecture GPU with fifth-generation Tensor Cores |
|
CPU |
14-core Arm Neoverse-V3AE 64- bit CPU 64 KB I-cache, 64 KB dCache 1 MB L2 cache per core 16 MB shared system L3 cache |
||
|
CPU maximum operating frequency |
2.6 GHz |
||
|
Vision Accelerator |
1x PVA v3 |
||
|
Memory |
128 GB 256-bit LPDDR5X 273 GB/s |
28 GB 256-bit LPDDR5X | 273 GB/s 96 GB dGPU memory | 1,792 GB/s |
128 GB 256-bit LPDDR5X | 273 GB/s 48 GB dGPU memory | 1,344 GB/s |
|
Storage |
Supports NVMe through PCIe Supports SSD through USB 3.2 |
4x SATA connectorsM.2 key M connector (PCIe Gen5 x2) |
4x SATA connectorsM.2 key M connector (PCIe Gen5 x2) |
|
Video Encoding |
2x NVEncode |
2x NVEncode (iGPU) 4x NVEncode (dGPU) |
2x NVEncode (iGPU) 3x NVEncode (dGPU) |
|
Video Decoding |
2x NVDecode |
2x NVDecode (iGPU) 4x NVDecode (dGPU) |
2x NVDecode (iGPU) 3x NVDecode (dGPU) |
|
PCIe |
Up to 8 lanes: Gen5 Root port only: C1 (x1) and C3 (x2) Root point or endpoint: C2 (x1), C4 (x8), and C5 (x4) |
2x PCIe Gen5 (x8, x16) |
|
|
USB |
xHCI host controller with integrated PHY (up to) 3x USB 3.2 4x USB 2.0 |
1x USB 3.2 Type-C 4x USB 3.2 Type A |
|
|
network |
4x 25GbE |
2x RJ45 (1GbE each) 2x QSFP28 (200GbE each) |
|
|
Connect X compatible |
No |
Yes |
|
|
display |
1x shared HDMI 2.1 1x VESA DisplayPort 1.4a: HBR2, MST |
1x VESA DisplayPort 1.4a |
|
|
Other I/O |
2x 13-pin CAN header 2x 6-pin automation header 2x 5-pin header JTAG connector 1x 4-pin fan connector: 12V, PWM, and tach 2x 5-pin audio panel header 2-pin RTC backup battery connector |
2x USB header for optional connection via cable 4x COM Ports 1x LPT 1x TPM 1x CAN 1x GPIO Audio Line-out, Mic In |
|
|
BMC |
- |
Yes |
|
|
Safety Support |
Functional Safety Island on SoC |
Functional Safety Island on SoC Safety MCU on the carrier board |
|
|
NVIDIA AI Enterprise Support |
Yes |
||
|
Power Consumption |
40 W–130 W |
40 W–130 W TMP Up to 300 W for dGPU |
|
|
size |
100mm x 87mm 699 pin B2B connector Integrated thermal transfer plate (TTP) with heat pipe |
243.84 mm x 198.98 mm x 31.05 mm |
|
NVIDIA IGX Thor Developer Kit
|
dGPU options |
With NVIDIA RTX Pro 6000 Blackwell Max-Q Workstation Edition |
With NVIDIA RTX™ Pro Blackwell 5000 |
|
dGPU performance |
24,064-core Blackwell architecture GPU with fifth-generation Tensor Cores |
14,080-core Blackwell architecture GPU with fifth-generation Tensor Cores |
|
Memory |
128 GB 256-bit LPDDR5X | 273 GB/s 96 GB dGPU memory | 1,792 GB/s |
128 GB 256-bit LPDDR5X | 273 GB/s 48 GB dGPU memory | 1,344 GB/s |
|
Storage |
1 TB M.2 NVMe (PCIE Gen5 x2) |
1 TB M.2 NVMe (PCIE Gen5 x2) |
|
PCIe |
2x PCIe Gen5 (x8, x16) |
|
|
USB |
1x USB 3.2 gen 2 type C connector 4x USB 3.2 gen 2 type A connectors |
|
|
Network |
2x RJ45 (1GbE each) 2x QSFP28 (200GbE each) |
|
|
Connect X compatible |
Yes |
|
|
Display |
DisplayPort 1.4a output |
|
|
Other I/O |
1x FSI CAN |
|
|
BMC |
Yes |
|
|
Functional safety |
Functional Safety Island on SoC Safety MCU on the carrier board |
|
|
NVIDIA AI Enterprise Support |
Yes |
|
|
Power Consumption |
40 W–130 W TMP Up to 300 W for dGPU |
|
|
Size |
262.70 mm × 382.70mm × 151.20mm |
|
NVIDIA IGX Thor Developer Kit Mini
|
dGPU |
No |
|
memory |
128 GB 256-bit LPDDR5X 273 GB/s |
|
Storage |
1TB NVMe M.2 Key M Slot |
|
PCIe |
M.2 Key M slot with x4 PCIe Gen5 (populated with 1 TB NVMe) M.2 Key E slot with x1 PCIe Gen5 (Populated with WiFi 6e + Bluetooth Module) |
|
USB |
2x USB Type-A 3.2 Gen2 2x USB Type-C 3.1 1x USB Type-C - (Debug purpose only) |
|
network |
1x 5GBe RJ45 connector 1x QSFP28 (4x 25GbE) WiFi 6E (Populated on M.2 Key E slot with x1 PCIe Gen5) |
|
display |
1x HDMI 2.0b 1x DisplayPort 1.4a |
|
OtherI/O |
2x 13-pin CAN header 2x 6-pin Automation header 2x 5-pin header JTAG Connector 1x 4-pin Fan Connector—12 V, PWM, and Tach 2x 5-pin Audio Panel Header 2-pin RTC Backup Battery Connector Microfit Power Jack Power, Force Recovery, and Reset buttons |
|
Functional safety |
Yes |
|
Safety MUC |
Renesas RH850/U2A16 |
|
Power consumption |
40 W–130 W |
|
size |
243.19 mm x 112.40 mm x 56.88 mm (height includes feet, carrier board, module, and thermal solution) |
Contact Us
*This form is for corporate use only.