Product Compare
NVIDIA GRID M10 8Q vs NVIDIA CMP 170HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | May 2016 | Sep 2021 |
| Generation | GRID | Mining GPUs |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x4 |
| Clock Speeds | ||
| Base Clock | 1033 MHz | 1140 MHz |
| Boost Clock | 1306 MHz | 1410 MHz |
| Memory Clock | 1300 MHz | 1458 MHz |
| Memory | ||
| Memory Size | 8GB | 16GB |
| Memory Type | GDDR5 | HBM2e |
| Memory Bus | 128bit | 4096bit |
| Bandwidth | 83.20GB/s | 1493GB/s |
| Render Config | ||
| Shading Units | 640 | 4480 |
| TMUs | 40 | 280 |
| ROPs | 16 | 128 |
| L1 Cache | 64 KB (per SMM) | 192 KB (per SM) |
| L2 Cache | 2 MB | 8 MB |
| SM Count | 70 | |
| Tensor Cores | 280 | |
| Theoretical Performance | ||
| Pixel Rate | 20.90 GPixel/s | 180.5 GPixel/s |
| Texture Rate | 52.24 GTexel/s | 394.8 GTexel/s |
| FP32 (float) | 1.672 TFLOPS | 12.63 TFLOPS |
| FP64 (double) | 52.24 GFLOPS | 6.317 TFLOPS |
| FP16 (half) | 50.53 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GM107 | GA100 |
| GPU Variant | GM107-570-A2 | GA100-105F-A1 |
| Architecture | Maxwell | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 7 nm |
| Transistors | 1.87 billion | 54.2 billion |
| Die Size | 148 mm² | 826 mm² |
| Board Design | ||
| TDP | 225W | 250W |
| Suggested PSU | 550 W | 600 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 8-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 (11_0) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 5.0 | 8.0 |
| Shader Model | 5.1 | N/A |