Quick/Comparisons
57 | Gaming | 19 |
55 | Workstation | 14 |
48 | AI/ML |
Compare with something else?
Compare GeForce RTX 4080 with another →9 |
45 | Energy Efficiency | 89 |
53 | Quick Comparison Final Score | 28 |
| AD104 (GN21-X9) | Graphics Processor | — |
| 7424 | Cores | 1024 |
| 232 / 80 | TMUs / ROPs | 64 / 32 |
| 5463.87 | Blender GPU | — |
| 120 | Forza Horizon 5 | — |
| 163 | The Witcher 3 | — |
| 209 | Counter-Strike 2 | — |
| 139 | Far Cry 6 | — |
| 98 | Hogwarts Legacy | — |
| 153 | Call of Duty | — |
| 92 | Ghost of Tsushima | — |
| 122 | Cyberpunk 2077 | — |
| 208 | Tomb Raider | — |
| 145 | Average FPS | — |
| 171 | 1080p High | — |
| 145 | 1080p Ultra | — |
| 112 | 1440p Ultra | — |
| 66 | 4K Ultra | — |
| Low | Margin of Error | — |
| 170767 | GB6 Compute Score | 30062 |
| 328.9 img/sec | Background Blur | 66.6 img/sec |
| 192.3 img/sec | Face Detection | 28.4 img/sec |
| 6.51 Gpixels/sec | Horizon Detection | 0.87 Gpixels/sec |
| 9.11 Gpixels/sec | Edge Detection | 1.24 Gpixels/sec |
| 10.1 Gpixels/sec | Gaussian Blur | 1.82 Gpixels/sec |
| 1.56 Gpixels/sec | Feature Matching | 0.3 Gpixels/sec |
| 660.7 Gpixels/sec | Stereo Matching | 102.4 Gpixels/sec |
| 20765.5 FPS | Particle Physics | 6543.8 FPS |
| OpenCL | API | OpenCL |
| 24711 | G3D Mark Score | — |
| 922 | G2D Mark | — |
| 241 FPS | DirectX 11 | — |
| 96 FPS | DirectX 12 | — |
| 11008 Ops/s | GPU Compute | — |
| 26637 | GB6 ML Single Precision | 4697 |
| 39211 | GB6 ML Half Precision | 7702 |
| 19995 | GB6 ML Quantized | 3445 |
| 10385 | Image Classification (SP) | 2540 |
| 25896 | Image Segmentation (HP) | 7387 |
| 27816 | Image Super Resolution (Q) | 4047 |
| 51976 | Face Detection (HP) | 8563 |
| 142459 | Pose Estimation (Q) | 11171 |
| 3405 | Text Classification (SP) | 819 |
| 4860 | Machine Translation (HP) | 2228 |
| 13308 | Object Detection (SP) | 2725 |
| 49203 | Depth Estimation (Q) | 7794 |
| 262792 | Style Transfer (SP) | 34572 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 133-182 GPixel/s | Pixel Fill Rate | 70-75 GPixel/s |
| 386-529 GTexel/s | Texture Fill Rate | 141-150 GTexel/s |
| 24.7-33.9 TFLOPS | FLOPS (FP32) | 4.5-4.8 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 12 GB | Memory Size | — |
| 2250 MHz | Memory Clock | — |
| 18000 Mbps | Effective Memory Speed | — |
| 192-bit | Bus | — |
| No | ECC | — |
| 432 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | Ring Bus |
| 60-175 W (configurable) | TGP | 28 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 295 mm² | Die Size | — |
| 35.8 billion | Transistor Count | — |
| 121.36 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| February 8, 2023 | Released | December 14, 2023 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Mid-range |
| Ada Lovelace | Architecture | Xe LPG |
| AD104 (GN21-X9) | GPU Codename | — |
| -Intel Core Ultra 9 185Hor above | Recommended CPU | -Intel Core Ultra 5 135Hor above |
| 11837 | Port Royal | — |
| 19263 | Steel Nomad Lite Score | — |
| 18832 | Time Spy | — |
| 85404 | Solar Bay | — |
| 41182 | Fire Strike | — |
| 36965 | Wild Life Extreme | — |
| 147212 | Night Raid | — |
| 1290-1860 MHz (configurable) | Base Clock | 300 MHz |
| 1665-2280 MHz (configurable) | Boost Clock | 2200-2350 MHz (configurable) |
| 7424 | Shading Units | 1024 |
| 232 | Texture Mapping Units (TMUs) | 64 |
| 80 | Render Output Units (ROPs) | 32 |
| 58 | Compute Units (Pipelines) | 128 |
| 232 | Tensor Cores | — |
| 58 | Ray-tracing Cores | 8 |
| 128KB per cluster | L1 Cache | 1536KB shared |
| 48MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |