Product Compare
NVIDIA P102 100 vs NVIDIA RTX PRO 4000 Blackwell
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Feb 2018 | Mar 2025 |
| Generation | Mining GPUs | Blackwell PRO W |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 3.0 x4 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1582 MHz | 1230 MHz |
| Boost Clock | 1683 MHz | 2055 MHz |
| Memory Clock | 1376 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 5GB | 24GB |
| Memory Type | GDDR5X | GDDR7 |
| Memory Bus | 320bit | 192bit |
| Bandwidth | 440.3GB/s | 672.0GB/s |
| Render Config | ||
| SM Count | 25 | 70 |
| Shading Units | 3200 | 8960 |
| TMUs | 200 | 280 |
| ROPs | 80 | 96 |
| L1 Cache | 48 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 0 MB | 48 MB |
| Tensor Cores | 280 | |
| RT Cores | 70 | |
| Theoretical Performance | ||
| Pixel Rate | 134.6 GPixel/s | 197.3 GPixel/s |
| Texture Rate | 336.6 GTexel/s | 575.4 GTexel/s |
| FP16 (half) | 168.3 GFLOPS | 36.83 TFLOPS |
| FP32 (float) | 10.77 TFLOPS | 36.83 TFLOPS |
| FP64 (double) | 336.6 GFLOPS | 575.4 GFLOPS |
| Graphics Processor | ||
| GPU Name | GP102 | GB203 |
| GPU Variant | GP102-100-A1 | |
| Architecture | Pascal | Blackwell 2.0 |
| Foundry | TSMC | TSMC |
| Process Size | 16 nm | 5 nm |
| Transistors | 11.8 billion | 45.6 billion |
| Die Size | 471 mm² | 378 mm² |
| Board Design | ||
| TDP | 250W | 140W |
| Suggested PSU | 600 W | 300 W |
| Outputs | No outputs | 4x DisplayPort 2.1b |
| Power Connectors | 2x 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 | 6.4 | 6.8 |