Quick/Comparisons
61 | Gaming | 56 |
62 | Workstation | 55 |
54 | AI/ML |
Compare with something else?
Compare GeForce RTX 4070 with another →54 |
46 | Energy Efficiency | 45 |
60 | Quick Comparison Final Score | 55 |
| AD104 | Graphics Processor | Navi 32 |
| 7168 | Cores | 3840 |
| 224 / 80 | TMUs / ROPs | 240 / 96 |
| 6153.24 | Blender GPU | 2417.04 |
| 131 | Forza Horizon 5 | 136 |
| 176 | The Witcher 3 | 177 |
| 212 | Counter-Strike 2 | 205 |
| 145 | Far Cry 6 | 146 |
| 106 | Hogwarts Legacy | 102 |
| 165 | Call of Duty | 164 |
| 100 | Ghost of Tsushima | 102 |
| 131 | Cyberpunk 2077 | 122 |
| 226 | Tomb Raider | 193 |
| 155 | Average FPS | 150 |
| 183 | 1080p High | 181 |
| 155 | 1080p Ultra | 150 |
| 120 | 1440p Ultra | 114 |
| 70 | 4K Ultra | 67 |
| Low | Margin of Error | Low |
| 206598 | GB6 Compute Score | 148335 |
| 359.5 img/sec | Background Blur | 300.7 img/sec |
| 210 img/sec | Face Detection | 200.5 img/sec |
| 7.61 Gpixels/sec | Horizon Detection | 5.77 Gpixels/sec |
| 10.4 Gpixels/sec | Edge Detection | 8.05 Gpixels/sec |
| 11.3 Gpixels/sec | Gaussian Blur | 6.44 Gpixels/sec |
| 1.97 Gpixels/sec | Feature Matching | 1.25 Gpixels/sec |
| 969.3 Gpixels/sec | Stereo Matching | 566.4 Gpixels/sec |
| 29061.4 FPS | Particle Physics | 20533.6 FPS |
| OpenCL | API | OpenCL |
| 29964 | G3D Mark Score | 24337 |
| 1193 | G2D Mark | 1191 |
| 271 FPS | DirectX 11 | 249 FPS |
| 110 FPS | DirectX 12 | 95 FPS |
| 16985 Ops/s | GPU Compute | 13568 Ops/s |
| 30706 | GB6 ML Single Precision | 31216 |
| 43851 | GB6 ML Half Precision | 37266 |
| 23776 | GB6 ML Quantized | 24564 |
| 12146 | Image Classification (SP) | 13913 |
| 23932 | Image Segmentation (HP) | 18416 |
| 36321 | Image Super Resolution (Q) | 31387 |
| 52836 | Face Detection (HP) | 51780 |
| 179788 | Pose Estimation (Q) | 177217 |
| 3371 | Text Classification (SP) | 3655 |
| 5017 | Machine Translation (HP) | 6216 |
| 15164 | Object Detection (SP) | 15073 |
| 62500 | Depth Estimation (Q) | 57318 |
| 357489 | Style Transfer (SP) | 347420 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 198 GPixel/s | Pixel Fill Rate | 233 GPixel/s |
| 554 GTexel/s | Texture Fill Rate | 583 GTexel/s |
| 35.5 TFLOPS | FLOPS (FP32) | 37.3 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 12 GB | Memory Size | 16 GB |
| 1313 MHz | Memory Clock | 2438 MHz |
| 21000 Mbps | Effective Memory Speed | 19500 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 504.2 GB/s | Memory Bandwidth | 624.1 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 220 W | TGP | 263 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 294 mm² | Die Size | 346 mm² |
| 35 billion | Transistor Count | 28 billion |
| 119.05 MTr/mm² | Transistor Density | 80.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| January 17, 2024 | Released | September 6, 2023 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 3.0 |
| AD104 | GPU Codename | Navi 32 |
| -Intel Core i7 14700Kor above | Recommended CPU | -Intel Core i5 13600Kor above |
| 21568 | Steel Nomad Lite Score | 18090 |
| 20882 | Time Spy | 20088 |
| 98166 | Solar Bay | 80288 |
| 13122 | Port Royal | 10921 |
| 50092 | Fire Strike | 50041 |
| 41630 | Wild Life Extreme | 37094 |
| 164777 | Night Raid | 160328 |
| 1980 MHz | Base Clock | 1295 MHz |
| 2475 MHz | Boost Clock | 2430 MHz |
| 7168 | Shading Units | 3840 |
| 224 | Texture Mapping Units (TMUs) | 240 |
| 80 | Render Output Units (ROPs) | 96 |
| 56 | Compute Units (Pipelines) | — |
| 224 | Tensor Cores | — |
| 56 | Ray-tracing Cores | 60 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |