Quick/Comparisons
61 | Gaming | 14 |
62 | Workstation | 21 |
54 | AI/ML |
Compare with something else?
Compare GeForce RTX 4070 with another →11 |
46 | Energy Efficiency | 68 |
60 | Quick Comparison Final Score | 25 |
| AD104 | Graphics Processor | TU117 |
| 7168 | Cores | 896 |
| 224 / 80 | TMUs / ROPs | 56 / 32 |
| 6153.24 | Blender GPU | 417.51 |
| 131 | Forza Horizon 5 | — |
| 176 | The Witcher 3 | — |
| 212 | Counter-Strike 2 | — |
| 145 | Far Cry 6 | — |
| 106 | Hogwarts Legacy | — |
| 165 | Call of Duty | — |
| 100 | Ghost of Tsushima | — |
| 131 | Cyberpunk 2077 | — |
| 226 | Tomb Raider | — |
| 155 | Average FPS | — |
| 183 | 1080p High | — |
| 155 | 1080p Ultra | — |
| 120 | 1440p Ultra | — |
| 70 | 4K Ultra | — |
| Low | Margin of Error | — |
| 206598 | GB6 Compute Score | 33110 |
| 359.5 img/sec | Background Blur | 61.6 img/sec |
| 210 img/sec | Face Detection | 31.3 img/sec |
| 7.61 Gpixels/sec | Horizon Detection | 1.17 Gpixels/sec |
| 10.4 Gpixels/sec | Edge Detection | 1.48 Gpixels/sec |
| 11.3 Gpixels/sec | Gaussian Blur | 1.8 Gpixels/sec |
| 1.97 Gpixels/sec | Feature Matching | 0.43 Gpixels/sec |
| 969.3 Gpixels/sec | Stereo Matching | 149.1 Gpixels/sec |
| 29061.4 FPS | Particle Physics | 4185.6 FPS |
| OpenCL | API | OpenCL |
| 29964 | G3D Mark Score | 7038 |
| 1193 | G2D Mark | 482 |
| 271 FPS | DirectX 11 | 51 FPS |
| 110 FPS | DirectX 12 | 32 FPS |
| 16985 Ops/s | GPU Compute | 2678 Ops/s |
| 30706 | GB6 ML Single Precision | 6235 |
| 43851 | GB6 ML Half Precision | 4946 |
| 23776 | GB6 ML Quantized | 4599 |
| 12146 | Image Classification (SP) | 2490 |
| 23932 | Image Segmentation (HP) | 3507 |
| 36321 | Image Super Resolution (Q) | 6427 |
| 52836 | Face Detection (HP) | 5241 |
| 179788 | Pose Estimation (Q) | 21102 |
| 3371 | Text Classification (SP) | 1520 |
| 5017 | Machine Translation (HP) | 2350 |
| 15164 | Object Detection (SP) | 2982 |
| 62500 | Depth Estimation (Q) | 10665 |
| 357489 | Style Transfer (SP) | 43183 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 198 GPixel/s | Pixel Fill Rate | 45 GPixel/s |
| 554 GTexel/s | Texture Fill Rate | 78 GTexel/s |
| 35.5 TFLOPS | FLOPS (FP32) | 2.5 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 12 GB | Memory Size | 4 GB |
| 1313 MHz | Memory Clock | 1250 MHz |
| 21000 Mbps | Effective Memory Speed | 10000 Mbps |
| 192-bit | Bus | 128-bit |
| No | ECC | — |
| 504.2 GB/s | Memory Bandwidth | 160 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 3.0 x16 |
| 220 W | TGP | 40 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 12 nm |
| 294 mm² | Die Size | 200 mm² |
| 35 billion | Transistor Count | 4.7 billion |
| 119.05 MTr/mm² | Transistor Density | 23.5 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 7.5 |
| Yes | Ray Tracing | No |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 1.4 |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 17, 2024 | Released | April 12, 2021 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | Entry-level |
| Ada Lovelace | Architecture | Turing |
| AD104 | GPU Codename | TU117 |
| -Intel Core i7 14700Kor above | Recommended CPU | -Intel Core i7 11800Hor above |
| 21568 | Steel Nomad Lite Score | — |
| 20882 | Time Spy | — |
| 98166 | Solar Bay | — |
| 13122 | Port Royal | — |
| 50092 | Fire Strike | — |
| 41630 | Wild Life Extreme | — |
| 164777 | Night Raid | — |
| 1980 MHz | Base Clock | 930 MHz |
| 2475 MHz | Boost Clock | 1395 MHz |
| 7168 | Shading Units | 896 |
| 224 | Texture Mapping Units (TMUs) | 56 |
| 80 | Render Output Units (ROPs) | 32 |
| 56 | Compute Units (Pipelines) | 14 |
| 224 | Tensor Cores | — |
| 56 | Ray-tracing Cores | — |
| 128KB per cluster | L1 Cache | 64KB per cluster |
| 48MB shared | L2 Cache | 1MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |