Product Compare
NVIDIA RTX A5500 Max-Q vs NVIDIA H100 CNX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2022 | Mar 2023 |
| Generation | Ampere-MW | Tesla Hopper |
| Type | Professional | AI GPU |
| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 585 MHz | 690 MHz |
| Boost Clock | 1260 MHz | 1845 MHz |
| Memory Clock | 1750 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 16GB | 80GB |
| Memory Type | GDDR6 | HBM2e |
| Memory Bus | 256bit | 5120bit |
| Bandwidth | 448.0GB/s | 2039GB/s |
| Render Config | ||
| SM Count | 58 | 114 |
| Shading Units | 7424 | 14592 |
| TMUs | 232 | 456 |
| ROPs | 96 | 24 |
| Tensor Cores | 232 | 456 |
| RT Cores | 58 | |
| L1 Cache | 128 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 4 MB | 50 MB |
| Theoretical Performance | ||
| Pixel Rate | 121.0 GPixel/s | 44.28 GPixel/s |
| Texture Rate | 292.3 GTexel/s | 841.3 GTexel/s |
| FP16 (half) | 18.71 TFLOPS | 215.4 TFLOPS |
| FP32 (float) | 18.71 TFLOPS | 53.84 TFLOPS |
| FP64 (double) | 292.3 GFLOPS | 26.92 TFLOPS |
| Graphics Processor | ||
| GPU Name | GA103 | GH100 |
| Architecture | Ampere | Hopper |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 4 nm |
| Transistors | 22 billion | 80 billion |
| Die Size | 496 mm² | 814 mm² |
| Board Design | ||
| TDP | 80W | 350W |
| Outputs | Portable Device Dependent | No outputs |
| Power Connectors | None | 8-pin EPS |
| Suggested PSU | 750 W | |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 8.6 | 9.0 |
| Shader Model | 6.8 | N/A |