Product Compare
NVIDIA Quadro K2200 vs NVIDIA H100 SXM5 64 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jul 2014 | Mar 2023 |
| Generation | Quadro | Tesla Hopper |
| Type | Professional | AI GPU |
| Bus Interface | PCIe 2.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1046 MHz | 1665 MHz |
| Boost Clock | 1124 MHz | 1980 MHz |
| Memory Clock | 1253 MHz | 1313 MHz |
| Memory | ||
| Memory Size | 4GB | 64GB |
| Memory Type | GDDR5 | HBM3 |
| Memory Bus | 128bit | 3072bit |
| Bandwidth | 80.19GB/s | 2.02TB/s |
| Render Config | ||
| Shading Units | 640 | 16896 |
| TMUs | 40 | 528 |
| ROPs | 16 | 24 |
| L1 Cache | 64 KB (per SMM) | 256 KB (per SM) |
| L2 Cache | 2 MB | 30 MB |
| SM Count | 132 | |
| Tensor Cores | 528 | |
| Theoretical Performance | ||
| Pixel Rate | 17.98 GPixel/s | 47.52 GPixel/s |
| Texture Rate | 44.96 GTexel/s | 1045 GTexel/s |
| FP32 (float) | 1439 GFLOPS | 66.91 TFLOPS |
| FP64 (double) | 44.96 GFLOPS | 33.45 TFLOPS |
| FP16 (half) | 267.6 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GM107 | GH100 |
| Architecture | Maxwell | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 5 nm |
| Transistors | 1.87 billion | 80 billion |
| Die Size | 148 mm² | 814 mm² |
| Board Design | ||
| TDP | 68W | 700W |
| Suggested PSU | 250 W | 1100 W |
| Outputs | 1x DVI2x DisplayPort 1.4a | No outputs |
| Power Connectors | None | 8-pin EPS |
| Graphics Features | ||
| DirectX | 12 (11_0) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 5.0 | 9.0 |
| Shader Model | 5.1 | N/A |