Product Compare
NVIDIA RTX PRO 5000 Blackwell Embedded vs NVIDIA H100 SXM5
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Unknown | Mar 2022 |
| Generation | Blackwell-MW | Tesla Hopper |
| Type | Mobile | AI GPU |
| Bus Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1095 MHz | 1590 MHz |
| Boost Clock | 1740 MHz | 1980 MHz |
| Memory Clock | 1750 MHz | 1313 MHz |
| Memory | ||
| Memory Size | 24GB | 80GB |
| Memory Type | GDDR7 | HBM3 |
| Memory Bus | 256bit | 5120bit |
| Bandwidth | 896.0GB/s | 3350GB/s |
| Render Config | ||
| SM Count | 82 | 132 |
| Shading Units | 10496 | 16896 |
| TMUs | 328 | 528 |
| ROPs | 112 | 24 |
| Tensor Cores | 328 | 528 |
| RT Cores | 82 | |
| L1 Cache | 128 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 64 MB | 50 MB |
| Theoretical Performance | ||
| Pixel Rate | 194.9 GPixel/s | 47.52 GPixel/s |
| Texture Rate | 570.7 GTexel/s | 1045 GTexel/s |
| FP16 (half) | 36.53 TFLOPS | 267.6 TFLOPS |
| FP32 (float) | 36.53 TFLOPS | 66.91 TFLOPS |
| FP64 (double) | 570.7 GFLOPS | 33.45 TFLOPS |
| Graphics Processor | ||
| GPU Name | GB203 | GH100 |
| Architecture | Blackwell 2.0 | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 4 nm |
| Transistors | 45.6 billion | 80 billion |
| Die Size | 378 mm² | 814 mm² |
| Board Design | ||
| TDP | 95W | 700W |
| Outputs | Portable Device Dependent | No outputs |
| Power Connectors | None | 8-pin EPS |
| Suggested PSU | 1100 W | |
| 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 | 9.0 |
| Shader Model | 6.8 | N/A |