Product Compare
NVIDIA P104 100 vs NVIDIA RTX PRO 5000 72 GB Blackwell
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Dec 2017 | Oct 2025 |
| Generation | Mining GPUs | Blackwell PRO W |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 1.0 x4 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1607 MHz | 1740 MHz |
| Boost Clock | 1733 MHz | 2377 MHz |
| Memory Clock | 1251 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 4GB | 72GB |
| Memory Type | GDDR5X | GDDR7 |
| Memory Bus | 256bit | 384bit |
| Bandwidth | 320.3GB/s | 1.34TB/s |
| Render Config | ||
| SM Count | 15 | 110 |
| Shading Units | 1920 | 14080 |
| TMUs | 120 | 440 |
| ROPs | 64 | 160 |
| L1 Cache | 48 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 2 MB | 96 MB |
| Tensor Cores | 440 | |
| RT Cores | 110 | |
| Theoretical Performance | ||
| Pixel Rate | 110.9 GPixel/s | 380.3 GPixel/s |
| Texture Rate | 208.0 GTexel/s | 1045.9 GTexel/s |
| FP16 (half) | 104.0 GFLOPS | 66.94 TFLOPS |
| FP32 (float) | 6.655 TFLOPS | 66.94 TFLOPS |
| FP64 (double) | 208.0 GFLOPS | 1045.9 GFLOPS |
| Graphics Processor | ||
| GPU Name | GP104 | GB202 |
| GPU Variant | GP104-100-A1 | |
| Architecture | Pascal | Blackwell 2.0 |
| Foundry | TSMC | TSMC |
| Process Size | 16 nm | 5 nm |
| Transistors | 7.2 billion | 92.2 billion |
| Die Size | 314 mm² | 750 mm² |
| Board Design | ||
| TDP | Unknown | 300W |
| Suggested PSU | 200 W | 700 W |
| Outputs | No outputs | 4x DisplayPort 2.1b |
| Power Connectors | 1x 8-pin | 1x 16-pin |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.4 |
| CUDA | 6.1 | 12.0 |
| Shader Model | 6.8 | 6.9 |