Quick/Comparisons
92 | Gaming | 10 |
91 | Workstation | 15 |
76 | AI/ML |
Compare with something else?
Compare GeForce RTX 4090 with another →17 |
43 | Energy Efficiency | 93 |
89 | Quick Comparison Final Score | 26 |
| AD102 | Graphics Processor | Phoenix |
| 16384 | Cores | 768 |
| 512 / 176 | TMUs / ROPs | 48 / 32 |
| 11688.48 | Blender GPU | 264.51 |
| 203 | Forza Horizon 5 | 24 |
| 270 | The Witcher 3 | 24 |
| 245 | Counter-Strike 2 | 29 |
| 183 | Far Cry 6 | 30 |
| 165 | Hogwarts Legacy | 14 |
| 269 | Call of Duty | 31 |
| 150 | Ghost of Tsushima | 14 |
| 204 | Cyberpunk 2077 | 18 |
| 283 | Tomb Raider | 29 |
| 219 | Average FPS | 24 |
| 256 | 1080p High | 31 |
| 219 | 1080p Ultra | 24 |
| 176 | 1440p Ultra | 16 |
| 107 | 4K Ultra | 9 |
| Low | Margin of Error | Low |
| 2.38 Gpixels/sec | Feature Matching | 0.41 Gpixels/sec |
| 1950 Gpixels/sec | Stereo Matching | 132.4 Gpixels/sec |
| 48090.4 FPS | Particle Physics | 4470.7 FPS |
| OpenCL | API | OpenCL |
| 316301 | GB6 Compute Score | 32713 |
| 318.9 img/sec | Background Blur | 86.4 img/sec |
| 222.8 img/sec | Face Detection | 35.8 img/sec |
| 14.2 Gpixels/sec | Horizon Detection | 1.03 Gpixels/sec |
| 21 Gpixels/sec | Edge Detection | 1.36 Gpixels/sec |
| 23.9 Gpixels/sec | Gaussian Blur | 1.41 Gpixels/sec |
| 38071 | G3D Mark Score | 6851 |
| 1303 | G2D Mark | 889 |
| 324 FPS | DirectX 11 | 66 FPS |
| 151 FPS | DirectX 12 | 30 FPS |
| 26193 Ops/s | GPU Compute | 3620 Ops/s |
| 42962 | GB6 ML Single Precision | 9091 |
| 59636 | GB6 ML Half Precision | 13510 |
| 31670 | GB6 ML Quantized | 6786 |
| 15600 | Image Classification (SP) | 3860 |
| 36657 | Image Segmentation (HP) | 5435 |
| 48114 | Image Super Resolution (Q) | 10580 |
| 78111 | Face Detection (HP) | 12855 |
| 289639 | Pose Estimation (Q) | 34716 |
| 4074 | Text Classification (SP) | 2578 |
| 6349 | Machine Translation (HP) | 3897 |
| 21186 | Object Detection (SP) | 3078 |
| 75599 | Depth Estimation (Q) | 14989 |
| 601428 | Style Transfer (SP) | 78608 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 444 GPixel/s | Pixel Fill Rate | 86-90 GPixel/s |
| 1290 GTexel/s | Texture Fill Rate | 130-134 GTexel/s |
| 82.6 TFLOPS | FLOPS (FP32) | 4.1-4.3 TFLOPS |
| GDDR6X | Memory Type | System Shared |
| 24 GB | Memory Size | — |
| 2625 MHz | Memory Clock | — |
| 21000 Mbps | Effective Memory Speed | — |
| 384-bit | Bus | — |
| No | ECC | — |
| 1010 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 450 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 609 mm² | Die Size | 178 mm² |
| 76.3 billion | Transistor Count | 25.4 billion |
| 125.29 MTr/mm² | Transistor Density | 142.7 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| September 20, 2022 | Released | January 4, 2023 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Mid-range |
| Ada Lovelace | Architecture | RDNA 3.0 |
| AD102 | GPU Codename | Phoenix |
| -Intel Core i9 14900Kor above | Recommended CPU | -AMD Ryzen 7 7840Uor above |
| 42169 | Steel Nomad Lite Score | 2662 |
| 36311 | Time Spy | 2787 |
| 187386 | Solar Bay | 11490 |
| 26128 | Port Royal | 1579 |
| 72387 | Fire Strike | 7881 |
| 85230 | Wild Life Extreme | 5315 |
| 195880 | Night Raid | 33499 |
| 2235 MHz | Base Clock | 800 MHz |
| 2520 MHz | Boost Clock | 2700-2800 MHz (configurable) |
| 16384 | Shading Units | 768 |
| 512 | Texture Mapping Units (TMUs) | 48 |
| 176 | Render Output Units (ROPs) | 32 |
| 128 | Compute Units (Pipelines) | 12 |
| 512 | Tensor Cores | — |
| 128 | Ray-tracing Cores | 12 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 72MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |