Product Compare
NVIDIA GeForce RTX 4080 12 GB vs NVIDIA H200 SXM 141 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Unknown | Nov 2024 |
| Generation | GeForce 40 | Server Hopper |
| Type | Desktop | AI GPU |
| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 2310 MHz | 1500 MHz |
| Boost Clock | 2610 MHz | 1980 MHz |
| Memory Clock | 1313 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 12GB | 141GB |
| Memory Type | GDDR6X | HBM3e |
| Memory Bus | 192bit | 6144bit |
| Bandwidth | 504.2GB/s | 4.89TB/s |
| Render Config | ||
| SM Count | 60 | 132 |
| Shading Units | 7680 | 16896 |
| TMUs | 240 | 528 |
| ROPs | 80 | 24 |
| Tensor Cores | 240 | 528 |
| RT Cores | 60 | |
| L1 Cache | 128 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 48 MB | 50 MB |
| Theoretical Performance | ||
| Pixel Rate | 208.8 GPixel/s | 47.52 GPixel/s |
| Texture Rate | 626.4 GTexel/s | 1045.4 GTexel/s |
| FP16 (half) | 40.09 TFLOPS | 267.6 TFLOPS |
| FP32 (float) | 40.09 TFLOPS | 66.91 TFLOPS |
| FP64 (double) | 626.4 GFLOPS | 33.45 TFLOPS |
| Graphics Processor | ||
| GPU Name | AD104 | GH100 |
| GPU Variant | AD104-400-A1 | |
| Architecture | Ada Lovelace | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 4 nm | 5 nm |
| Transistors | 35.8 billion | 80 billion |
| Die Size | 295 mm² | 814 mm² |
| Board Design | ||
| TDP | 285W | 700W |
| Suggested PSU | 600 W | 1100 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | 8-pin EPS |
| 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 | 8.9 | 9.0 |
| Shader Model | 6.6 | N/A |