Language :
NVIDIA IGX™ is an industrial-grade, edge AI platform that combines enterprise-level hardware, software, and support. It's purpose-built for industrial, robotics, and medical environments, delivering powerful AI compute, high-bandwidth sensor processing, enterprise security, and robot safety. The platform also comes with NVIDIA AI Enterprise and up to 10 years of support, so you can deliver AI safely and securely to support human and machine collaboration.
NVIDIA IGX Thor™ represents a new class of enterprise edge computers, built to power the next generation of industrial, robotics, and medical edge applications. Taking advantage of the NVIDIA Blackwell GPU architecture, it excels at generative reasoning and multimodal sensor processing.
Read BlogExplore high-performance and energy-efficient systems built for low-latency, real-time applications
Build robot safety AI agents for industrial robots with NVIDIA Halos, which integrates functional safety and proactive AI safety for autonomous machines.
NVIDIA AI Enterprise software with 10 years of NVIDIA enterprise support keeps applications accelerated and secured even in the most challenging conditions.
IGX is production-ready, combining industrial-grade hardware with enterprise software and support.
The NVIDIA IGX Thor Platform unlocks real-time sensor processing and AI reasoning for physical AI agents with industrial-grade hardware, enterprise software, and functional safety. It's powered by the NVIDIA Blackwell Architecture iGPU and an optional dGPU, delivering up to 5581 FP4 TFLOPS of AI compute to effortlessly run multiple generative AI models at the edge. Compared to NVIDIA IGX Orin™, it provides up to 8x higher AI compute on iGPU, 2.5x higher AI compute on dGPU, and 2x better connectivity.
NVIDIA AI Enterprise software powers edge AI on NVIDIA IGX Thor, ensuring mission-critical performance, security, and long-term enterprise support across the entire stack. It seamlessly runs generative AI—from VLA models like NVIDIA Isaac GR00T N to popular LLMs and VLMs such as Cosmos Reason—and brings cloud-native NVIDIA AI Enterprise and NVIDIA NIM™ to the edge. Applications include NVIDIA Isaac for robotics, Metropolis for visual AI, Holoscan for sensor processing, and NVIDIA Halos safety AI agents, giving your organization a secure, stable, and high-performance experience for next-gen physical AI.
The development kit for all IGX Thor use cases.
The development kit for robotic safety.
Intelligent machines augment the work of doctors, nurses, and surgeons in smart hospitals, using AI to enable better patient outcomes. NVIDIA Holoscan running on IGX delivers real-time AI at the clinical edge and positions developers to quickly take to market the next generation of AI-enabled medical devices.
Learn MoreSoftware-driven solutions are replacing or enhancing traditional hardware-based instruments used in fields like visual processing and semiconductor testing. These software-defined approaches allow users to adjust and reconfigure parameters without hardware changes, facilitating quick prototyping, customization, and integration with AI-based applications.
Learn MoreIntegrating AI into industrial robotics improves efficiency, flexibility, and safety by enhancing perception, decision-making, and adaptive behavior. This integration, combined with strict safety protocols, optimizes robotic operations in manufacturing settings.
Learn MoreGet started with more resources, including documentation and software downloads.
| dGPU Option | With NVIDIA RTX PRO™ 6000 Blackwell Max-Q Workstation Edition | With NVIDIA RTX PRO™ Blackwell 5000 |
| AI Performance | Up to 5,581 TFLOPS (FP4-Sparse) | Up to 4,293 TFLOPS (FP4-Sparse) |
| iGPU | 2,560-core NVIDIA Blackwell architecture GPU with 96 fifth-generation Tensor Cores Multi-Instance GPU with 10 TPCs |
2,560-core NVIDIA Blackwell architecture GPU with 96 fifth-generation Tensor Cores Multi-Instance GPU with 10 TPCs |
| iGPU Max Frequency | 1.57 GHz | 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 |
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 Max Frequency | 2.6 GHz | 2.6 GHz |
| Vision Accelerator | 1x PVA v3 | 1x PVA v3 |
| 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) |
| Video Encode | 2x NVEncode (iGPU) 4x NVEncode (dGPU) |
2x NVEncode (iGPU) 4x NVEncode (dGPU) |
| Video Decode | 2x NVDecode (iGPU) 4x NVDecode (dGPU) |
2x NVDecode (iGPU) 4x NVDecode (dGPU) |
| PCIe | 2x PCIe Gen5 (x8, x16) | 2x PCIe Gen5 (x8, x16) |
| USB | 1x USB 3.2 gen 2 type C connector 4x USB 3.2 gen 2 type A connectors |
1x USB 3.2 gen 2 type C connector 4x USB 3.2 gen 2 type A connectors |
| Networking | 2x RJ45 (1GbE each) 2x QSFP28 (200GbE each) |
2x RJ45 (1GbE each) 2x QSFP28 (200GbE each) |
| ConnectX Support | Yes | Yes |
| Display | DisplayPort 1.4a output | DisplayPort 1.4a output |
| Other I/O | 1x FSI CAN Audio Line-out, MIC in |
1x FSI CAN Audio Line-out, MIC in |
| BMC | Yes | Yes |
| Functional Safety | Functional Safety Island on SoC Safety MCU on the carrier board |
Functional Safety Island on SoC Safety MCU on the carrier board |
| NVDIA AI Enterprise Support | Yes | Yes |
| Power | 40 W–130 W TMP Up to 300 W for dGPU |
40 W–130 W TMP Up to 300 W for dGPU |
| Mechanical | 262.70 mm × 382.70mm × 151.20mm | 262.70 mm × 382.70mm × 151.20mm |
Future
