C931
*NVIDIA® Grace Blackwell Architecture:
- NVIDIA Blackwell GPU & Arm 20-core CPU
- NVIDIA® NVLink®-C2C CPU-GPU memory interconnect
*128 GB LPDDR5x coherent, unified system memory
*1000 AI FLOPS (FP4) AI performance
*Full stack solution, hardware & software, designed for AI developers
- NVIDIA Blackwell GPU & Arm 20-core CPU
- NVIDIA® NVLink®-C2C CPU-GPU memory interconnect
*128 GB LPDDR5x coherent, unified system memory
*1000 AI FLOPS (FP4) AI performance
*Full stack solution, hardware & software, designed for AI developers
Seamless AI Model Scaling from Desktop to Cloud
Leverage NVIDIA’s AI software architecture to seamlessly scale from desktop to NVIDIA DGX™ cloud or other NVIDIA® accelerated data centers or cloudinfrastructures, just with minimal code changes.
| C931 | |
| Architecture | NVIDIA Grace Blackwell |
| GPUs | NVIDIA Blackwell Architecture |
| CPU | 20 core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm |
| Tensor Performance | 1000 AI TOPS (FP4, Sparse) |
| Ethernet | 1x RJ-45 connector 10 GbE |
|
System
Memory
|
128 GB LPDDR5x,
unified system memory
|
| NIC | ConnectX-7 Smart NIC |
|
Memory
Interface
|
256-bit
|
|
Memory
Bandwidth
|
273 GB/s
|
| Audio-output | HDMI multichannel audio output |
| Wi-Fi | WiFi 7 |
|
Storage
|
1 or 4 TB NVME.M2 with self-encryption |
| OS | NVIDIA DGX™ OS |