Product Compare
NVIDIA Tesla K40st vs NVIDIA GeForce RTX 4070 Max-Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2013 | Jan 2023 |
| Generation | Tesla | GeForce 40 Mobile |
| Type | Professional | Mobile |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |
| Clock Speeds | ||
| Memory Clock | 1502 MHz | 2000 MHz |
| Base Clock | 735 MHz | |
| Boost Clock | 1230 MHz | |
| Memory | ||
| Memory Size | 12GB | 8GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 384bit | 128bit |
| Bandwidth | 288.4GB/s | 256.0GB/s |
| Render Config | ||
| Shading Units | 2880 | 4608 |
| TMUs | 240 | 144 |
| ROPs | 48 | 48 |
| L1 Cache | 16 KB (per SMX) | 128 KB (per SM) |
| L2 Cache | 1536 KB | 32 MB |
| SM Count | 36 | |
| Tensor Cores | 144 | |
| RT Cores | 36 | |
| Theoretical Performance | ||
| Pixel Rate | 34.50 GPixel/s | 59.04 GPixel/s |
| Texture Rate | 138.0 GTexel/s | 177.1 GTexel/s |
| FP32 (float) | 3.312 TFLOPS | 11.34 TFLOPS |
| FP64 (double) | 1104 GFLOPS | 177.1 GFLOPS |
| FP16 (half) | 11.34 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110B | AD106 |
| Architecture | Kepler | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 5 nm |
| Transistors | 7.08 billion | 22.9 billion |
| Die Size | 561 mm² | 188 mm² |
| GPU Variant | GN21-X6 | |
| Board Design | ||
| TDP | 245W | 35W |
| Suggested PSU | 550 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | 12 (11_1) | 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 | 6.8 |