Specifications
| Architecture | NVIDIA Blackwell Architecture |
| Process Size | 4N NVIDIA Custom Process |
| Die Size | 750 mm 2 |
| CUDA Parallel Processing Cores | 24,064 |
| NVIDIA Tensor Cores | 752 |
| NVIDIA RT Cores | 188 |
| Single-Precision Performance | 125 TFLOPS |
| AI Performance | 4000 AI TOPS2 |
| RT Core Performance | 380 TFLOPS |
| GPU Memory | 96 GB GDDR7 with ECC |
| Memory Interface | 512-bit |
| Memory Bandwidth | 1792 GB/s |
| Max Power Consumption | 600W |
| Graphics Bus | PCI Express 5.0 x16 |
| Display Connectors | DP 2.1 (4) |
| Form Factor | 5.4” H x 12” L, XHFL Dual Slot |
| Power Connector | 1x PCIe CEM5 16-pin |
Key Features
- Architecture: NVIDIA Blackwell Architecture
- CUDA Cores: 24,064 parallel processing cores
- Tensor Cores: 752 for AI acceleration
- RT Cores: 188 for real‑time ray tracing
- Memory: 96 GB GDDR7 with ECC, 512‑bit interface
- Bandwidth: 1,792 GB/s memory bandwidth
- Power & Connectivity: 600W max power, PCIe 5.0 x16, 4× DisplayPort 2.1
There are no reviews yet.