Quick/Comparisons
The GeForce RTX 4080 takes the lead in gaming performance with an impressive 80 score, outpacing the GeForce RTX 4070's 54 score.
The GeForce RTX 4080 edges out the GeForce RTX 4070 in content creation with a 71 score, thanks to its slightly better workstation performance.
The GeForce RTX 4080 takes the lead in AI and machine learning with a 66 score, outperforming the GeForce RTX 4070's 48 score.
54 | Gaming | 80 |
55 | Workstation | 71 |
48 | AI/ML | 66 |
44 | Energy Efficiency | 43 |
53 | Quick Comparison Final Score | 75 |
| AD104 | Graphics Processor | AD103 |
| 5888 | Cores | 9728 |
| 184 / 64 | TMUs / ROPs | 304 / 112 |
| 5394.14 | Blender GPU | 8710.73 |
| 114 | Forza Horizon 5 | — |
| 163 | The Witcher 3 | — |
| 202 | Counter-Strike 2 | — |
| 135 | Far Cry 6 | — |
| 96 | Hogwarts Legacy | — |
| 143 | Call of Duty | — |
| 89 | Ghost of Tsushima | — |
| 115 | Cyberpunk 2077 | — |
| 196 | Tomb Raider | — |
| 139 | Average FPS | — |
| 165 | 1080p High | — |
| 139 | 1080p Ultra | — |
| 107 | 1440p Ultra | — |
| 63 | 4K Ultra | — |
| Low | Margin of Error | — |
| 167522 | GB6 Compute Score | 217712 |
| 233 img/sec | Background Blur | 250.4 img/sec |
| 141.7 img/sec | Face Detection | 190 img/sec |
| 6.62 Gpixels/sec | Horizon Detection | 9.56 Gpixels/sec |
| 9.19 Gpixels/sec | Edge Detection | 12.8 Gpixels/sec |
| 9.2 Gpixels/sec | Gaussian Blur | 15.3 Gpixels/sec |
| 1.78 Gpixels/sec | Feature Matching | 1.97 Gpixels/sec |
| 845.4 Gpixels/sec | Stereo Matching | 1130 Gpixels/sec |
| 25043.9 FPS | Particle Physics | 28795.5 FPS |
| OpenCL | API | OpenCL |
| 26921 | G3D Mark Score | 34430 |
| 1168 | G2D Mark | 1250 |
| 243 FPS | DirectX 11 | 313 FPS |
| 103 FPS | DirectX 12 | 132 FPS |
| 14623 Ops/s | GPU Compute | 20406 Ops/s |
| 27166 | GB6 ML Single Precision | 36799 |
| 40963 | GB6 ML Half Precision | 53331 |
| 20332 | GB6 ML Quantized | 28104 |
| 10246 | Image Classification (SP) | 13466 |
| 26153 | Image Segmentation (HP) | 34767 |
| 32054 | Image Super Resolution (Q) | 42687 |
| 51337 | Face Detection (HP) | 70927 |
| 124617 | Pose Estimation (Q) | 239350 |
| 3703 | Text Classification (SP) | 3606 |
| 5484 | Machine Translation (HP) | 6519 |
| 13134 | Object Detection (SP) | 18153 |
| 50548 | Depth Estimation (Q) | 65667 |
| 263477 | Style Transfer (SP) | 414848 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 158 GPixel/s | Pixel Fill Rate | 281 GPixel/s |
| 455 GTexel/s | Texture Fill Rate | 762 GTexel/s |
| 29.1 TFLOPS | FLOPS (FP32) | 48.7 TFLOPS |
| GDDR6X | Memory Type | GDDR6X |
| 12 GB | Memory Size | 16 GB |
| 1313 MHz | Memory Clock | 1400 MHz |
| 21000 Mbps | Effective Memory Speed | 22400 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 504 GB/s | Memory Bandwidth | 716.8 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 200 W | TGP | 320 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 294 mm² | Die Size | 379 mm² |
| 35 billion | Transistor Count | 45 billion |
| 119.05 MTr/mm² | Transistor Density | 118.73 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 13, 2023 | Released | September 20, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Ada Lovelace | Architecture | Ada Lovelace |
| AD104 | GPU Codename | AD103 |
| -Intel Core i7 14700Kor above | Recommended CPU | -Intel Core i7 14700Kor above |
| 18089 | Steel Nomad Lite Score | 30172 |
| 17806 | Time Spy | 28161 |
| 82784 | Solar Bay | 136931 |
| 11154 | Port Royal | 17982 |
| 44075 | Fire Strike | 64633 |
| 35470 | Wild Life Extreme | 59111 |
| 153508 | Night Raid | 184963 |
| 1920 MHz | Base Clock | 2205 MHz |
| 2475 MHz | Boost Clock | 2505 MHz |
| 5888 | Shading Units | 9728 |
| 184 | Texture Mapping Units (TMUs) | 304 |
| 64 | Render Output Units (ROPs) | 112 |
| 46 | Compute Units (Pipelines) | 76 |
| 184 | Tensor Cores | 304 |
| 46 | Ray-tracing Cores | 76 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 36MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 4070 with another →