Product Compare
NVIDIA GeForce RTX 5070 Ti vs NVIDIA Tesla P4
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Feb 2025 | Sep 2016 |
| Generation | GeForce 50 | Tesla |
| Type | Desktop | Professional |
| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 2295 MHz | 886 MHz |
| Boost Clock | 2452 MHz | 1114 MHz |
| Memory Clock | 1750 MHz | 1502 MHz |
| Memory | ||
| Memory Size | 16GB | 8GB |
| Memory Type | GDDR7 | GDDR5 |
| Memory Bus | 256bit | 256bit |
| Bandwidth | 896.0GB/s | 192.3GB/s |
| Render Config | ||
| SM Count | 70 | 20 |
| Shading Units | 8960 | 2560 |
| TMUs | 280 | 160 |
| ROPs | 96 | 64 |
| Tensor Cores | 280 | |
| RT Cores | 70 | |
| L1 Cache | 128 KB (per SM) | 48 KB (per SM) |
| L2 Cache | 48 MB | 2 MB |
| Theoretical Performance | ||
| Pixel Rate | 235.4 GPixel/s | 71.30 GPixel/s |
| Texture Rate | 686.6 GTexel/s | 178.2 GTexel/s |
| FP16 (half) | 43.94 TFLOPS | 89.12 GFLOPS |
| FP32 (float) | 43.94 TFLOPS | 5.704 TFLOPS |
| FP64 (double) | 686.6 GFLOPS | 178.2 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB203 | GP104 |
| GPU Variant | GB203-300-A1 | GP104-895-A1 |
| Architecture | Blackwell 2.0 | Pascal |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 16 nm |
| Transistors | 45.6 billion | 7.2 billion |
| Die Size | 378 mm² | 314 mm² |
| Board Design | ||
| TDP | 300W | 75W |
| Suggested PSU | 700 W | 250 W |
| Outputs | 1x HDMI 2.1b3x DisplayPort 2.1b | No outputs |
| Power Connectors | 1x 16-pin | None |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | 1.3 |
| CUDA | 12.0 | 6.1 |
| Shader Model | 6.8 | 6.4 |