Product Compare
Intel Data Center GPU Max 1350 vs NVIDIA Rubin GPU
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2023 | Jan 2026 |
| Generation | Data Center GPU | Server Rubin |
| Type | Professional | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 6.0 x16 |
| Clock Speeds | ||
| Base Clock | 750 MHz | 700 MHz |
| Boost Clock | 1550 MHz | 2267 MHz |
| Memory Clock | 1200 MHz | 2695 MHz |
| Memory | ||
| Memory Size | 96GB | 288GB |
| Memory Type | HBM2e | HBM4 |
| Memory Bus | 8192bit | 16384bit |
| Bandwidth | 2458GB/s | 22.1TB/s |
| Render Config | ||
| Shading Units | 14336 | 28672 |
| TMUs | 896 | 896 |
| ROPs | 0 | 24 |
| Tensor Cores | 896 | 896 |
| RT Cores | 112 | |
| L1 Cache | 64 KB (per EU) | 256 KB (per SM) |
| L2 Cache | 408 MB | 128 MB |
| SM Count | 224 | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 54.41 GPixel/s |
| Texture Rate | 1389 GTexel/s | 2031.2 GTexel/s |
| FP16 (half) | 44.44 TFLOPS | 260.0 TFLOPS |
| FP32 (float) | 44.44 TFLOPS | 130.0 TFLOPS |
| FP64 (double) | 44.44 TFLOPS | 32.50 TFLOPS |
| Graphics Processor | ||
| GPU Name | Ponte Vecchio | GR100 |
| Architecture | Generation 12.5 | Rubin |
| Foundry | Intel | TSMC |
| Process Size | 10 nm | 3 nm |
| Transistors | 100 billion | 336 billion |
| Die Size | 1280 mm² | 1456 mm² |
| Board Design | ||
| TDP | 450W | 2300W |
| Suggested PSU | 850 W | 2700 W |
| Outputs | No outputs | No outputs |
| Graphics Features | ||
| DirectX | 12 (12_1) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | N/A |
| Shader Model | 6.6 | N/A |
| CUDA | 10.7 | |