Product Compare
NVIDIA Quadro T2000 Max Q vs NVIDIA PG506 242
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | May 2019 | Apr 2021 |
| Generation | Quadro Mobile | Tesla |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1200 MHz | 930 MHz |
| Boost Clock | 1620 MHz | 1440 MHz |
| Memory Clock | 1751 MHz | 1215 MHz |
| Memory | ||
| Memory Size | 4GB | 24GB |
| Memory Type | GDDR5 | HBM2 |
| Memory Bus | 128bit | 3072bit |
| Bandwidth | 112.1GB/s | 933.1GB/s |
| Render Config | ||
| SM Count | 16 | 56 |
| Shading Units | 1024 | 3584 |
| TMUs | 64 | 224 |
| ROPs | 32 | 96 |
| L1 Cache | 64 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 1024 KB | 24 MB |
| Tensor Cores | 224 | |
| Theoretical Performance | ||
| Pixel Rate | 51.84 GPixel/s | 138.2 GPixel/s |
| Texture Rate | 103.7 GTexel/s | 322.6 GTexel/s |
| FP16 (half) | 6.636 TFLOPS | 10.32 TFLOPS |
| FP32 (float) | 3.318 TFLOPS | 10.32 TFLOPS |
| FP64 (double) | 103.7 GFLOPS | 5.161 TFLOPS |
| Graphics Processor | ||
| GPU Name | TU117 | GA100 |
| Architecture | Turing | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 12 nm | 7 nm |
| Transistors | 4.7 billion | 54.2 billion |
| Die Size | 200 mm² | 826 mm² |
| Board Design | ||
| TDP | 40W | 165W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | 8-pin EPS |
| Suggested PSU | 450 W | |
| Graphics Features | ||
| DirectX | 12 (12_1) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 7.5 | 8.0 |
| Shader Model | 6.6 | N/A |