Product Compare
NVIDIA H100 SXM5 96 GB vs NVIDIA GeForce RTX 4080 Max-Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2023 | Jan 2023 |
| Generation | Server Hopper | GeForce 40 Mobile |
| Type | AI GPU | Mobile |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1350 MHz | 795 MHz |
| Boost Clock | 1980 MHz | 1350 MHz |
| Memory Clock | 1313 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 96GB | 12GB |
| Memory Type | HBM3 | GDDR6 |
| Memory Bus | 5120bit | 192bit |
| Bandwidth | 3.36TB/s | 336.0GB/s |
| Render Config | ||
| SM Count | 132 | 58 |
| Shading Units | 16896 | 7424 |
| TMUs | 528 | 232 |
| ROPs | 24 | 80 |
| Tensor Cores | 528 | 232 |
| L1 Cache | 256 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 50 MB | 48 MB |
| RT Cores | 58 | |
| Theoretical Performance | ||
| Pixel Rate | 47.52 GPixel/s | 108.0 GPixel/s |
| Texture Rate | 1045 GTexel/s | 313.2 GTexel/s |
| FP16 (half) | 267.6 TFLOPS | 20.04 TFLOPS |
| FP32 (float) | 66.91 TFLOPS | 20.04 TFLOPS |
| FP64 (double) | 33.45 TFLOPS | 313.2 GFLOPS |
| Graphics Processor | ||
| GPU Name | GH100 | AD104 |
| Architecture | Hopper | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 4 nm |
| Transistors | 80 billion | 35.8 billion |
| Die Size | 814 mm² | 295 mm² |
| GPU Variant | GN21-X9 | |
| Board Design | ||
| TDP | 700W | 60W |
| 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 | 8.9 |
| Shader Model | N/A | 6.7 |