Product Compare
NVIDIA GRID K280Q vs NVIDIA CMP 90HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jun 2013 | Jul 2021 |
| Generation | GRID | Mining GPUs |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 1.0 x4 |
| Clock Speeds | ||
| Memory Clock | 1250 MHz | 1188 MHz |
| Base Clock | 1500 MHz | |
| Boost Clock | 1710 MHz | |
| Memory | ||
| Memory Size | 4GB | 10GB |
| Memory Type | GDDR5 | GDDR6X |
| Memory Bus | 256bit | 320bit |
| Bandwidth | 160.0GB/s | 760.3GB/s |
| Render Config | ||
| Shading Units | 1536 | 6400 |
| TMUs | 128 | 200 |
| ROPs | 32 | 80 |
| L1 Cache | 16 KB (per SMX) | 128 KB (per SM) |
| L2 Cache | 512 KB | 5 MB |
| SM Count | 50 | |
| Tensor Cores | 200 | |
| RT Cores | 50 | |
| Theoretical Performance | ||
| Pixel Rate | 23.84 GPixel/s | 136.8 GPixel/s |
| Texture Rate | 95.36 GTexel/s | 342.0 GTexel/s |
| FP32 (float) | 2.289 TFLOPS | 21.89 TFLOPS |
| FP64 (double) | 95.36 GFLOPS | 342.0 GFLOPS |
| FP16 (half) | 21.89 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK104 | GA102 |
| Architecture | Kepler | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 28 nm | 8 nm |
| Transistors | 3.54 billion | 28.3 billion |
| Die Size | 294 mm² | 628 mm² |
| GPU Variant | GA102-100-A1 | |
| Board Design | ||
| TDP | 225W | 320W |
| Suggested PSU | 550 W | 700 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 2x 8-pin | |
| Graphics Features | ||
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.3 |
| CUDA | 3.0 | 8.6 |
| Shader Model | 5.1 | 6.8 |