Product Compare
NVIDIA H100 PCIe 80 GB vs NVIDIA GeForce RTX 2070 SUPER
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2022 | Jul 2019 |
| Generation | Server Hopper | GeForce 20 |
| Type | AI GPU | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1095 MHz | 1605 MHz |
| Boost Clock | 1755 MHz | 1770 MHz |
| Memory Clock | 1593 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 80GB | 8GB |
| Memory Type | HBM2e | GDDR6 |
| Memory Bus | 5120bit | 256bit |
| Bandwidth | 2.04TB/s | 448.0GB/s |
| Render Config | ||
| SM Count | 114 | 40 |
| Shading Units | 14592 | 2560 |
| TMUs | 456 | 160 |
| ROPs | 24 | 64 |
| Tensor Cores | 456 | 320 |
| L1 Cache | 256 KB (per SM) | 64 KB (per SM) |
| L2 Cache | 50 MB | 4 MB |
| RT Cores | 40 | |
| Theoretical Performance | ||
| Pixel Rate | 42.12 GPixel/s | 113.3 GPixel/s |
| Texture Rate | 800.3 GTexel/s | 283.2 GTexel/s |
| FP16 (half) | 204.9 TFLOPS | 18.12 TFLOPS |
| FP32 (float) | 51.22 TFLOPS | 9.062 TFLOPS |
| FP64 (double) | 25.61 TFLOPS | 283.2 GFLOPS |
| Graphics Processor | ||
| GPU Name | GH100 | TU104 |
| Architecture | Hopper | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 12 nm |
| Transistors | 80 billion | 13.6 billion |
| Die Size | 814 mm² | 545 mm² |
| GPU Variant | TU104-410-A1 | |
| Board Design | ||
| TDP | 350W | 215W |
| Suggested PSU | 750 W | 550 W |
| Outputs | No outputs | 1x HDMI 2.03x DisplayPort 1.4a1x USB Type-C |
| Power Connectors | 1x 16-pin | 1x 6-pin + 1x 8-pin |
| 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 | 7.5 |
| Shader Model | N/A | 6.8 |