Product Compare
NVIDIA H100 SXM5 vs NVIDIA GeForce RTX 3050 Max-Q Refresh 4 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2022 | Jul 2022 |
| Generation | Tesla Hopper | GeForce 30 Mobile |
| Type | AI GPU | Mobile |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |
| Clock Speeds | ||
| Base Clock | 1590 MHz | 757 MHz |
| Boost Clock | 1980 MHz | 1125 MHz |
| Memory Clock | 1313 MHz | 1375 MHz |
| Memory | ||
| Memory Size | 80GB | 4GB |
| Memory Type | HBM3 | GDDR6 |
| Memory Bus | 5120bit | 128bit |
| Bandwidth | 3350GB/s | 176.0GB/s |
| Render Config | ||
| SM Count | 132 | 16 |
| Shading Units | 16896 | 2048 |
| TMUs | 528 | 64 |
| ROPs | 24 | 32 |
| Tensor Cores | 528 | 64 |
| L1 Cache | 256 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 50 MB | 2 MB |
| RT Cores | 16 | |
| Theoretical Performance | ||
| Pixel Rate | 47.52 GPixel/s | 36.00 GPixel/s |
| Texture Rate | 1045 GTexel/s | 72.00 GTexel/s |
| FP16 (half) | 267.6 TFLOPS | 4.608 TFLOPS |
| FP32 (float) | 66.91 TFLOPS | 4.608 TFLOPS |
| FP64 (double) | 33.45 TFLOPS | 72.00 GFLOPS |
| Graphics Processor | ||
| GPU Name | GH100 | GA107 |
| Architecture | Hopper | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 4 nm | 8 nm |
| Transistors | 80 billion | 8.7 billion |
| Die Size | 814 mm² | 200 mm² |
| Board Design | ||
| TDP | 700W | 35W |
| Suggested PSU | 1100 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | 8-pin EPS | None |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 9.0 | 8.6 |
| Shader Model | N/A | 6.7 |