Product Compare
AMD Radeon Instinct MI8 vs NVIDIA Quadro RTX 3000 Max Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Dec 2016 | May 2019 |
| Generation | Radeon Instinct | Quadro Mobile |
| Type | Professional | Professional |
| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Memory Clock | 500 MHz | 1500 MHz |
| Base Clock | 600 MHz | |
| Boost Clock | 1215 MHz | |
| Memory | ||
| Memory Size | 4GB | 6GB |
| Memory Type | HBM | GDDR6 |
| Memory Bus | 4096bit | 192bit |
| Bandwidth | 512.0GB/s | 288.0GB/s |
| Render Config | ||
| Compute Units | 64 | |
| Shading Units | 4096 | 1920 |
| TMUs | 256 | 120 |
| ROPs | 64 | 64 |
| L1 Cache | 16 KB (per CU) | 64 KB (per SM) |
| L2 Cache | 2 MB | 3 MB |
| SM Count | 30 | |
| Tensor Cores | 240 | |
| RT Cores | 30 | |
| Theoretical Performance | ||
| Pixel Rate | 64.00 GPixel/s | 77.76 GPixel/s |
| Texture Rate | 256.0 GTexel/s | 145.8 GTexel/s |
| FP16 (half) | 8.192 TFLOPS | 9.331 TFLOPS |
| FP32 (float) | 8.192 TFLOPS | 4.666 TFLOPS |
| FP64 (double) | 512.0 GFLOPS | 145.8 GFLOPS |
| Graphics Processor | ||
| GPU Name | Fiji | TU106 |
| GPU Variant | Fiji XT CA(215-0862120) | |
| Architecture | GCN 3.0 | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 12 nm |
| Transistors | 8.9 billion | 10.8 billion |
| Die Size | 596 mm² | 445 mm² |
| Board Design | ||
| TDP | 175W | 60W |
| Suggested PSU | 450 W | |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 8-pin | None |
| Graphics Features | ||
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2.170 | 1.3 |
| Shader Model | 6.5 | 6.6 |
| CUDA | 7.5 | |