Product Compare
NVIDIA GeForce RTX 5090 vs NVIDIA GeForce RTX 4070 10 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2025 | Unknown |
| Generation | GeForce 50 | GeForce 40 |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 2017 MHz | 2355 MHz |
| Boost Clock | 2407 MHz | 2520 MHz |
| Memory Clock | 1750 MHz | 1313 MHz |
| Memory | ||
| Memory Size | 32GB | 10GB |
| Memory Type | GDDR7 | GDDR6X |
| Memory Bus | 512bit | 160bit |
| Bandwidth | 1.79TB/s | 420.2GB/s |
| Render Config | ||
| SM Count | 170 | 56 |
| Shading Units | 21760 | 7168 |
| TMUs | 680 | 224 |
| ROPs | 176 | 80 |
| Tensor Cores | 680 | 224 |
| RT Cores | 170 | 56 |
| L1 Cache | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 96 MB | 48 MB |
| Theoretical Performance | ||
| Pixel Rate | 423.6 GPixel/s | 201.6 GPixel/s |
| Texture Rate | 1636.8 GTexel/s | 564.5 GTexel/s |
| FP16 (half) | 104.8 TFLOPS | 36.13 TFLOPS |
| FP32 (float) | 104.8 TFLOPS | 36.13 TFLOPS |
| FP64 (double) | 1.637 TFLOPS | 564.5 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB202 | AD104 |
| GPU Variant | GB202-300-A1 | AD104-275-A1 |
| 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 |
| Board Design | ||
| TDP | 575W | 220W |
| Suggested PSU | 950 W | 550 W |
| Outputs | 1x HDMI 2.1b3x 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 | 6.7 |