Product Compare
NVIDIA RTX PRO 4000 Blackwell Embedded vs NVIDIA CMP 170HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Unknown | Sep 2021 |
| Generation | Blackwell-MW | Mining GPUs |
| Type | Mobile | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x4 |
| Clock Speeds | ||
| Base Clock | 975 MHz | 1140 MHz |
| Boost Clock | 1702 MHz | 1410 MHz |
| Memory Clock | 1750 MHz | 1458 MHz |
| Memory | ||
| Memory Size | 16GB | 16GB |
| Memory Type | GDDR7 | HBM2e |
| Memory Bus | 256bit | 4096bit |
| Bandwidth | 896.0GB/s | 1493GB/s |
| Render Config | ||
| SM Count | 60 | 70 |
| Shading Units | 7680 | 4480 |
| TMUs | 240 | 280 |
| ROPs | 96 | 128 |
| Tensor Cores | 240 | 280 |
| RT Cores | 60 | |
| L1 Cache | 128 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 64 MB | 8 MB |
| Theoretical Performance | ||
| Pixel Rate | 163.4 GPixel/s | 180.5 GPixel/s |
| Texture Rate | 408.5 GTexel/s | 394.8 GTexel/s |
| FP16 (half) | 26.14 TFLOPS | 50.53 TFLOPS |
| FP32 (float) | 26.14 TFLOPS | 12.63 TFLOPS |
| FP64 (double) | 408.5 GFLOPS | 6.317 TFLOPS |
| Graphics Processor | ||
| GPU Name | GB203 | GA100 |
| Architecture | Blackwell 2.0 | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 7 nm |
| Transistors | 45.6 billion | 54.2 billion |
| Die Size | 378 mm² | 826 mm² |
| GPU Variant | GA100-105F-A1 | |
| Board Design | ||
| TDP | 80W | 250W |
| Outputs | Portable Device Dependent | No outputs |
| Power Connectors | None | 2x 8-pin |
| Suggested PSU | 600 W | |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | N/A |
| CUDA | 12.0 | 8.0 |
| Shader Model | 6.8 | N/A |