Product Compare
NVIDIA Tesla K20m vs NVIDIA GeForce RTX 4080 Max-Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2013 | Jan 2023 |
| Generation | Tesla | GeForce 40 Mobile |
| Type | Professional | Mobile |
| Bus Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1300 MHz | 1750 MHz |
| Base Clock | 795 MHz | |
| Boost Clock | 1350 MHz | |
| Memory | ||
| Memory Size | 5GB | 12GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 320bit | 192bit |
| Bandwidth | 208.0GB/s | 336.0GB/s |
| Render Config | ||
| Shading Units | 2496 | 7424 |
| TMUs | 208 | 232 |
| ROPs | 40 | 80 |
| L1 Cache | 16 KB (per SMX) | 128 KB (per SM) |
| L2 Cache | 1280 KB | 48 MB |
| SM Count | 58 | |
| Tensor Cores | 232 | |
| RT Cores | 58 | |
| Theoretical Performance | ||
| Pixel Rate | 36.71 GPixel/s | 108.0 GPixel/s |
| Texture Rate | 146.8 GTexel/s | 313.2 GTexel/s |
| FP32 (float) | 3.524 TFLOPS | 20.04 TFLOPS |
| FP64 (double) | 1175 GFLOPS | 313.2 GFLOPS |
| FP16 (half) | 20.04 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110 | AD104 |
| Architecture | Kepler | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 4 nm |
| Transistors | 7.08 billion | 35.8 billion |
| Die Size | 561 mm² | 295 mm² |
| GPU Variant | GN21-X9 | |
| Board Design | ||
| TDP | 225W | 60W |
| Suggested PSU | 550 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | 1x 6-pin + 1x 8-pin | None |
| 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 | 3.5 | 8.9 |
| Shader Model | 5.1 | 6.7 |