Product Compare
NVIDIA RTX PRO 5000 Blackwell vs NVIDIA GeForce RTX 4070 GDDR6
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2025 | Aug 2024 |
| Generation | Blackwell PRO W | GeForce 40 |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1740 MHz | 1920 MHz |
| Boost Clock | 2377 MHz | 2475 MHz |
| Memory Clock | 1750 MHz | 2500 MHz |
| Memory | ||
| Memory Size | 48GB | 12GB |
| Memory Type | GDDR7 | GDDR6 |
| Memory Bus | 384bit | 192bit |
| Bandwidth | 1.34TB/s | 480.0GB/s |
| Render Config | ||
| SM Count | 110 | 46 |
| Shading Units | 14080 | 5888 |
| TMUs | 440 | 184 |
| ROPs | 160 | 64 |
| Tensor Cores | 440 | 184 |
| RT Cores | 110 | 46 |
| L1 Cache | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 96 MB | 36 MB |
| Theoretical Performance | ||
| Pixel Rate | 380.3 GPixel/s | 158.4 GPixel/s |
| Texture Rate | 1045.9 GTexel/s | 455.4 GTexel/s |
| FP16 (half) | 66.94 TFLOPS | 29.15 TFLOPS |
| FP32 (float) | 66.94 TFLOPS | 29.15 TFLOPS |
| FP64 (double) | 1045.9 GFLOPS | 455.4 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB202 | AD104 |
| Architecture | Blackwell 2.0 | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 5 nm |
| Transistors | 92.2 billion | 35.8 billion |
| Die Size | 750 mm² | 294 mm² |
| GPU Variant | AD104-2XX-A1 | |
| Board Design | ||
| TDP | 300W | 200W |
| Suggested PSU | 700 W | 550 W |
| Outputs | 4x DisplayPort 2.1b | 1x HDMI 2.13x DisplayPort 1.4a |
| Power Connectors | 1x 16-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 | 1.4 | 1.3 |
| CUDA | 12.0 | 8.9 |
| Shader Model | 6.9 | 6.8 |