Product Compare
NVIDIA RTX A4000 Max-Q vs NVIDIA H200 NVL
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Apr 2021 | Nov 2024 |
| Generation | Ampere-MW | Server Hopper |
| Type | Mobile | AI GPU |
| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 780 MHz | 1365 MHz |
| Boost Clock | 1395 MHz | 1785 MHz |
| Memory Clock | 1375 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 8GB | 141GB |
| Memory Type | GDDR6 | HBM3e |
| Memory Bus | 256bit | 6144bit |
| Bandwidth | 352.0GB/s | 4.89TB/s |
| Render Config | ||
| SM Count | 40 | 132 |
| Shading Units | 5120 | 16896 |
| TMUs | 160 | 528 |
| ROPs | 80 | 24 |
| Tensor Cores | 160 | 528 |
| RT Cores | 40 | |
| L1 Cache | 128 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 4 MB | 50 MB |
| Theoretical Performance | ||
| Pixel Rate | 111.6 GPixel/s | 42.84 GPixel/s |
| Texture Rate | 223.2 GTexel/s | 942.5 GTexel/s |
| FP16 (half) | 14.28 TFLOPS | 241.3 TFLOPS |
| FP32 (float) | 14.28 TFLOPS | 60.32 TFLOPS |
| FP64 (double) | 223.2 GFLOPS | 30.16 TFLOPS |
| Graphics Processor | ||
| GPU Name | GA104 | GH100 |
| Architecture | Ampere | Hopper |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 5 nm |
| Transistors | 17.4 billion | 80 billion |
| Die Size | 392 mm² | 814 mm² |
| Board Design | ||
| TDP | 80W | 600W |
| Outputs | Portable Device Dependent | No outputs |
| Power Connectors | None | 8-pin EPS |
| Suggested PSU | 1000 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 |