Product Compare
NVIDIA RTX PRO 6000D Blackwell vs NVIDIA PG506 232
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2025 | Apr 2021 |
| Generation | Blackwell PRO W | Tesla |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1590 MHz | 930 MHz |
| Boost Clock | 2617 MHz | 1440 MHz |
| Memory Clock | 1750 MHz | 1215 MHz |
| Memory | ||
| Memory Size | 96GB | 24GB |
| Memory Type | GDDR7 | HBM2 |
| Memory Bus | 512bit | 3072bit |
| Bandwidth | 1.79TB/s | 933.1GB/s |
| Render Config | ||
| SM Count | 188 | 56 |
| Shading Units | 24064 | 3584 |
| TMUs | 752 | 224 |
| ROPs | 192 | 96 |
| Tensor Cores | 752 | 224 |
| RT Cores | 188 | |
| L1 Cache | 128 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 128 MB | 24 MB |
| Theoretical Performance | ||
| Pixel Rate | 502.5 GPixel/s | 138.2 GPixel/s |
| Texture Rate | 1968.0 GTexel/s | 322.6 GTexel/s |
| FP16 (half) | 126.0 TFLOPS | 10.32 TFLOPS |
| FP32 (float) | 126.0 TFLOPS | 10.32 TFLOPS |
| FP64 (double) | 1.968 TFLOPS | 5.161 TFLOPS |
| Graphics Processor | ||
| GPU Name | GB202 | GA100 |
| Architecture | Blackwell 2.0 | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 7 nm |
| Transistors | 92.2 billion | 54.2 billion |
| Die Size | 750 mm² | 826 mm² |
| Board Design | ||
| TDP | 600W | 165W |
| Suggested PSU | 1000 W | 450 W |
| Outputs | 4x DisplayPort 2.1b | No outputs |
| Power Connectors | 1x 16-pin | 8-pin EPS |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | N/A |
| CUDA | 12.0 | 8.0 |
| Shader Model | 6.8 | N/A |