Quick/Comparisons
54 | Gaming | 12 |
55 | Workstation | 23 |
48 | AI/ML |
Compare with something else?
Compare GeForce RTX 4070 with another →14 |
44 | Energy Efficiency | 72 |
53 | Quick Comparison Final Score | 25 |
| AD104 | Graphics Processor | GA107S |
| 5888 | Cores | 2048 |
| 184 / 64 | TMUs / ROPs | 64 / 32 |
| 5394.14 | Blender GPU | 692.94 |
| 114 | Forza Horizon 5 | 24 |
| 163 | The Witcher 3 | 26 |
| 202 | Counter-Strike 2 | 42 |
| 135 | Far Cry 6 | 33 |
| 96 | Hogwarts Legacy | 14 |
| 143 | Call of Duty | 26 |
| 89 | Ghost of Tsushima | 13 |
| 115 | Cyberpunk 2077 | 18 |
| 196 | Tomb Raider | 36 |
| 139 | Average FPS | 26 |
| 165 | 1080p High | 35 |
| 139 | 1080p Ultra | 26 |
| 107 | 1440p Ultra | 18 |
| 63 | 4K Ultra | 9 |
| Low | Margin of Error | Medium |
| 167522 | GB6 Compute Score | 40574 |
| 233 img/sec | Background Blur | 62.4 img/sec |
| 141.7 img/sec | Face Detection | 35.7 img/sec |
| 6.62 Gpixels/sec | Horizon Detection | 1.62 Gpixels/sec |
| 9.19 Gpixels/sec | Edge Detection | 2.11 Gpixels/sec |
| 9.2 Gpixels/sec | Gaussian Blur | 2.05 Gpixels/sec |
| 1.78 Gpixels/sec | Feature Matching | 0.52 Gpixels/sec |
| 845.4 Gpixels/sec | Stereo Matching | 185.1 Gpixels/sec |
| 25043.9 FPS | Particle Physics | 5502.5 FPS |
| OpenCL | API | OpenCL |
| 26921 | G3D Mark Score | 6570 |
| 1168 | G2D Mark | 416 |
| 243 FPS | DirectX 11 | 40 FPS |
| 103 FPS | DirectX 12 | 38 FPS |
| 14623 Ops/s | GPU Compute | 2911 Ops/s |
| 27166 | GB6 ML Single Precision | 7597 |
| 40963 | GB6 ML Half Precision | 15030 |
| 20332 | GB6 ML Quantized | 5337 |
| 10246 | Image Classification (SP) | 3298 |
| 26153 | Image Segmentation (HP) | 8358 |
| 32054 | Image Super Resolution (Q) | 6219 |
| 51337 | Face Detection (HP) | 14319 |
| 124617 | Pose Estimation (Q) | 22995 |
| 3703 | Text Classification (SP) | 2226 |
| 5484 | Machine Translation (HP) | 3163 |
| 13134 | Object Detection (SP) | 3768 |
| 50548 | Depth Estimation (Q) | 12079 |
| 263477 | Style Transfer (SP) | 53139 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 158 GPixel/s | Pixel Fill Rate | 24-55 GPixel/s |
| 455 GTexel/s | Texture Fill Rate | 48-109 GTexel/s |
| 29.1 TFLOPS | FLOPS (FP32) | 3.1-7 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 12 GB | Memory Size | 4 GB |
| 1313 MHz | Memory Clock | 1500 MHz |
| 21000 Mbps | Effective Memory Speed | 12000 Mbps |
| 192-bit | Bus | 64-bit |
| No | ECC | No |
| 504 GB/s | Memory Bandwidth | 96 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 200 W | TGP | 20-60 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 5 nm | Fabrication Process | 8 nm |
| 294 mm² | Die Size | 200 mm² |
| 35 billion | Transistor Count | 8.7 billion |
| 119.05 MTr/mm² | Transistor Density | 43.5 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 2 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 13, 2023 | Released | March 22, 2022 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | Entry-level |
| Ada Lovelace | Architecture | Ampere |
| AD104 | GPU Codename | GA107S |
| -Intel Core i7 14700Kor above | Recommended CPU | -Intel Core i7 12700Hor above |
| 18089 | Steel Nomad Lite Score | 3021 |
| 17806 | Time Spy | 3023 |
| 82784 | Solar Bay | 13710 |
| 11154 | Port Royal | 625 |
| 44075 | Fire Strike | 10265 |
| 35470 | Wild Life Extreme | 4053 |
| 153508 | Night Raid | 38312 |
| 1920 MHz | Base Clock | 370-890 MHz (configurable) |
| 2475 MHz | Boost Clock | 745-1710 MHz (configurable) |
| 5888 | Shading Units | 2048 |
| 184 | Texture Mapping Units (TMUs) | 64 |
| 64 | Render Output Units (ROPs) | 32 |
| 46 | Compute Units (Pipelines) | 16 |
| 184 | Tensor Cores | 64 |
| 46 | Ray-tracing Cores | 16 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 36MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |