Quick/Comparisons
57 | Gaming | 63 |
55 | Workstation | 63 |
48 | AI/ML |
Compare with something else?
Compare GeForce RTX 4080 with another →55 |
45 | Energy Efficiency | 45 |
53 | Quick Comparison Final Score | 59 |
| AD104 (GN21-X9) | Graphics Processor | AD103 (GN21-X11) |
| 7424 | Cores | 9728 |
| 232 / 80 | TMUs / ROPs | 304 / 112 |
| 5463.87 | Blender GPU | 7059.06 |
| 120 | Forza Horizon 5 | 131 |
| 163 | The Witcher 3 | 182 |
| 209 | Counter-Strike 2 | 208 |
| 139 | Far Cry 6 | 147 |
| 98 | Hogwarts Legacy | 108 |
| 153 | Call of Duty | 164 |
| 92 | Ghost of Tsushima | 100 |
| 122 | Cyberpunk 2077 | 137 |
| 208 | Tomb Raider | 231 |
| 145 | Average FPS | 156 |
| 171 | 1080p High | 187 |
| 145 | 1080p Ultra | 156 |
| 112 | 1440p Ultra | 123 |
| 66 | 4K Ultra | 72 |
| Low | Margin of Error | Low |
| 170767 | GB6 Compute Score | 203263 |
| 328.9 img/sec | Background Blur | 264 img/sec |
| 192.3 img/sec | Face Detection | 134.3 img/sec |
| 6.51 Gpixels/sec | Horizon Detection | 9.27 Gpixels/sec |
| 9.11 Gpixels/sec | Edge Detection | 12.7 Gpixels/sec |
| 10.1 Gpixels/sec | Gaussian Blur | 13.2 Gpixels/sec |
| 1.56 Gpixels/sec | Feature Matching | 1.92 Gpixels/sec |
| 660.7 Gpixels/sec | Stereo Matching | 1060 Gpixels/sec |
| 20765.5 FPS | Particle Physics | 29225.1 FPS |
| OpenCL | API | OpenCL |
| 24711 | G3D Mark Score | 27060 |
| 922 | G2D Mark | 988 |
| 241 FPS | DirectX 11 | 258 FPS |
| 96 FPS | DirectX 12 | 106 FPS |
| 11008 Ops/s | GPU Compute | 12206 Ops/s |
| 26637 | GB6 ML Single Precision | 29362 |
| 39211 | GB6 ML Half Precision | 42611 |
| 19995 | GB6 ML Quantized | 22212 |
| 10385 | Image Classification (SP) | 11346 |
| 25896 | Image Segmentation (HP) | 24625 |
| 27816 | Image Super Resolution (Q) | 36874 |
| 51976 | Face Detection (HP) | 50088 |
| 142459 | Pose Estimation (Q) | 174844 |
| 3405 | Text Classification (SP) | 3226 |
| 4860 | Machine Translation (HP) | 4905 |
| 13308 | Object Detection (SP) | 14667 |
| 49203 | Depth Estimation (Q) | 53868 |
| 262792 | Style Transfer (SP) | 340056 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 133-182 GPixel/s | Pixel Fill Rate | 163-228 GPixel/s |
| 386-529 GTexel/s | Texture Fill Rate | 442-620 GTexel/s |
| 24.7-33.9 TFLOPS | FLOPS (FP32) | 28.3-39.7 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 12 GB | Memory Size | 16 GB |
| 2250 MHz | Memory Clock | 2000 MHz |
| 18000 Mbps | Effective Memory Speed | 16000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 432 GB/s | Memory Bandwidth | 512 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 60-175 W (configurable) | TGP | 80-175 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 295 mm² | Die Size | 379 mm² |
| 35.8 billion | Transistor Count | 45.9 billion |
| 121.36 MTr/mm² | Transistor Density | 121.11 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 |
| February 8, 2023 | Released | February 8, 2023 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Ada Lovelace |
| AD104 (GN21-X9) | GPU Codename | AD103 (GN21-X11) |
| -Intel Core Ultra 9 185Hor above | Recommended CPU | -Intel Core Ultra 9 185Hor above |
| 11837 | Port Royal | 13733 |
| 19263 | Steel Nomad Lite Score | 22501 |
| 18832 | Time Spy | 21401 |
| 85404 | Solar Bay | 96130 |
| 41182 | Fire Strike | 45218 |
| 36965 | Wild Life Extreme | 42491 |
| 147212 | Night Raid | 147892 |
| 1290-1860 MHz (configurable) | Base Clock | 930-1620 MHz (configurable) |
| 1665-2280 MHz (configurable) | Boost Clock | 1455-2040 MHz (configurable) |
| 7424 | Shading Units | 9728 |
| 232 | Texture Mapping Units (TMUs) | 304 |
| 80 | Render Output Units (ROPs) | 112 |
| 58 | Compute Units (Pipelines) | 76 |
| 232 | Tensor Cores | 304 |
| 58 | Ray-tracing Cores | 76 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |