Quick/Comparisons
54 | Gaming | 80 |
55 | Workstation | 94 |
46 | AI/ML |
Compare with something else?
Compare GeForce RTX 5070 with another →75 |
61 | Energy Efficiency | 44 |
55 | Quick Comparison Final Score | 83 |
| GB205-200 | Graphics Processor | AD102 |
| 5888 | Cores | 18176 |
| 184 / 80 | TMUs / ROPs | 568 / 192 |
| 4935.31 | Blender GPU | 11038.91 |
| 114 | Forza Horizon 5 | 165 |
| 156 | The Witcher 3 | 219 |
| 208 | Counter-Strike 2 | 221 |
| 133 | Far Cry 6 | 164 |
| 97 | Hogwarts Legacy | 133 |
| 145 | Call of Duty | 216 |
| 88 | Ghost of Tsushima | 123 |
| 115 | Cyberpunk 2077 | 172 |
| 194 | Tomb Raider | 267 |
| 139 | Average FPS | 187 |
| 165 | 1080p High | 219 |
| 139 | 1080p Ultra | 187 |
| 106 | 1440p Ultra | 148 |
| 62 | 4K Ultra | 89 |
| Low | Margin of Error | High |
| 166122 | GB6 Compute Score | 389848 |
| 248 img/sec | Background Blur | 618.3 img/sec |
| 147.7 img/sec | Face Detection | 399.9 img/sec |
| 6.54 Gpixels/sec | Horizon Detection | 15.1 Gpixels/sec |
| 8.24 Gpixels/sec | Edge Detection | 22.1 Gpixels/sec |
| 9.55 Gpixels/sec | Gaussian Blur | 26.3 Gpixels/sec |
| 1.64 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 876 Gpixels/sec | Stereo Matching | 2210 Gpixels/sec |
| 24026.1 FPS | Particle Physics | 53494.5 FPS |
| OpenCL | API | OpenCL |
| 22633 | G3D Mark Score | 28613 |
| 967 | G2D Mark | 1005 |
| 236 FPS | DirectX 11 | 284 FPS |
| 101 FPS | DirectX 12 | 102 FPS |
| 8478 Ops/s | GPU Compute | 22439 Ops/s |
| 25374 | GB6 ML Single Precision | 37270 |
| 46076 | GB6 ML Half Precision | 53469 |
| 19458 | GB6 ML Quantized | 27850 |
| 10408 | Image Classification (SP) | 13367 |
| 29018 | Image Segmentation (HP) | 32477 |
| 26983 | Image Super Resolution (Q) | 42056 |
| 54398 | Face Detection (HP) | 69004 |
| 107270 | Pose Estimation (Q) | 230965 |
| 3658 | Text Classification (SP) | 3491 |
| 6237 | Machine Translation (HP) | 5545 |
| 13717 | Object Detection (SP) | 18668 |
| 49509 | Depth Estimation (Q) | 68370 |
| 199816 | Style Transfer (SP) | 520389 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 116-182 GPixel/s | Pixel Fill Rate | 481 GPixel/s |
| 266-420 GTexel/s | Texture Fill Rate | 1423 GTexel/s |
| 17-26.8 TFLOPS | FLOPS (FP32) | 91.1 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 12 GB | Memory Size | 48 GB |
| 1750 MHz | Memory Clock | 2500 MHz |
| 28000 Mbps | Effective Memory Speed | 20000 Mbps |
| 192-bit | Bus | 384-bit |
| No | ECC | No |
| 672 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 60-140 W (configurable) | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| 263 mm² | Die Size | 609 mm² |
| 31.1 billion | Transistor Count | 76 billion |
| 118.25 MTr/mm² | Transistor Density | 124.79 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 3 |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | December 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | High-end |
| Blackwell 2.0 | Architecture | Ada Lovelace |
| GB205-200 | GPU Codename | AD102 |
| -Intel Core Ultra 7 255HXor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 18210 | Steel Nomad Lite Score | 32284 |
| 17382 | Time Spy | 26686 |
| 77747 | Solar Bay | 145429 |
| 11320 | Port Royal | 19557 |
| 41818 | Fire Strike | 62803 |
| 33104 | Wild Life Extreme | 53640 |
| 158023 | Night Raid | 148225 |
| 847-1762 MHz (configurable) | Base Clock | 915 MHz |
| 1447-2280 MHz (configurable) | Boost Clock | 2505 MHz |
| 5888 | Shading Units | 18176 |
| 184 | Texture Mapping Units (TMUs) | 568 |
| 80 | Render Output Units (ROPs) | 192 |
| 46 | Compute Units (Pipelines) | 142 |
| 184 | Tensor Cores | 568 |
| 46 | Ray-tracing Cores | 142 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 96MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |