Product Compare
NVIDIA GRID RTX T10 16 vs NVIDIA L20
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Unknown | Nov 2023 |
| Generation | GRID | Server Ada |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1065 MHz | 1440 MHz |
| Boost Clock | 1395 MHz | 2520 MHz |
| Memory Clock | 1575 MHz | 2250 MHz |
| Memory | ||
| Memory Size | 16GB | 48GB |
| Memory Type | GDDR6 | GDDR6 |
| Memory Bus | 384bit | 384bit |
| Bandwidth | 604.8GB/s | 864.0GB/s |
| Render Config | ||
| SM Count | 56 | 92 |
| Shading Units | 3584 | 11776 |
| TMUs | 224 | 368 |
| ROPs | 64 | 128 |
| Tensor Cores | 448 | 368 |
| RT Cores | 56 | 92 |
| L1 Cache | 64 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 6 MB | 96 MB |
| Theoretical Performance | ||
| Pixel Rate | 89.28 GPixel/s | 322.6 GPixel/s |
| Texture Rate | 312.5 GTexel/s | 927.4 GTexel/s |
| FP16 (half) | 20.00 TFLOPS | 59.35 TFLOPS |
| FP32 (float) | 9.999 TFLOPS | 59.35 TFLOPS |
| FP64 (double) | 312.5 GFLOPS | 927.4 GFLOPS |
| Graphics Processor | ||
| GPU Name | TU102 | AD102 |
| GPU Variant | TU102-875-A1 | AD102 |
| Architecture | Turing | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 12 nm | 5 nm |
| Transistors | 18.6 billion | 76.3 billion |
| Die Size | 754 mm² | 609 mm² |
| Board Design | ||
| TDP | 150W | 275W |
| Suggested PSU | 450 W | 600 W |
| Outputs | No outputs | 4x DisplayPort 1.4a |
| Power Connectors | 1x 6-pin + 1x 8-pin | 1x 16-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.4 |
| CUDA | 7.5 | 8.9 |
| Shader Model | 6.8 | 6.9 |