Quick/Comparisons
92 | Gaming | 5 |
91 | Workstation | 13 |
76 | AI/ML |
Compare with something else?
Compare GeForce RTX 4090 with another →6 |
43 | Energy Efficiency | 75 |
89 | Quick Comparison Final Score | 19 |
| AD102 | Graphics Processor | — |
| 16384 | Cores | 448 |
| 512 / 176 | TMUs / ROPs | 28 / 8 |
| 11688.48 | Blender GPU | — |
| 203 | Forza Horizon 5 | 10 |
| 270 | The Witcher 3 | — |
| 245 | Counter-Strike 2 | 14 |
| 183 | Far Cry 6 | 11 |
| 165 | Hogwarts Legacy | - |
| 269 | Call of Duty | 13 |
| 150 | Ghost of Tsushima | - |
| 204 | Cyberpunk 2077 | - |
| 283 | Tomb Raider | 11 |
| 219 | Average FPS | 10 |
| 256 | 1080p High | 13 |
| 219 | 1080p Ultra | 10 |
| 176 | 1440p Ultra | - |
| 107 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 2.38 Gpixels/sec | Feature Matching | 0.21 Gpixels/sec |
| 1950 Gpixels/sec | Stereo Matching | 54.7 Gpixels/sec |
| 48090.4 FPS | Particle Physics | 1957.6 FPS |
| OpenCL | API | OpenCL |
| 316301 | GB6 Compute Score | 14408 |
| 318.9 img/sec | Background Blur | 33.7 img/sec |
| 222.8 img/sec | Face Detection | 15.4 img/sec |
| 14.2 Gpixels/sec | Horizon Detection | 0.35 Gpixels/sec |
| 21 Gpixels/sec | Edge Detection | 0.76 Gpixels/sec |
| 23.9 Gpixels/sec | Gaussian Blur | 0.69 Gpixels/sec |
| 38071 | G3D Mark Score | 2250 |
| 1303 | G2D Mark | 568 |
| 324 FPS | DirectX 11 | 16 FPS |
| 151 FPS | DirectX 12 | 11 FPS |
| 26193 Ops/s | GPU Compute | 1215 Ops/s |
| 42962 | GB6 ML Single Precision | 3157 |
| 59636 | GB6 ML Half Precision | 4191 |
| 31670 | GB6 ML Quantized | 2365 |
| 15600 | Image Classification (SP) | 1323 |
| 36657 | Image Segmentation (HP) | 1675 |
| 48114 | Image Super Resolution (Q) | 2919 |
| 78111 | Face Detection (HP) | 4386 |
| 289639 | Pose Estimation (Q) | 9348 |
| 4074 | Text Classification (SP) | 1024 |
| 6349 | Machine Translation (HP) | 1888 |
| 21186 | Object Detection (SP) | 1452 |
| 75599 | Depth Estimation (Q) | 5272 |
| 601428 | Style Transfer (SP) | 19585 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 444 GPixel/s | Pixel Fill Rate | 12-16 GPixel/s |
| 1290 GTexel/s | Texture Fill Rate | 42-56 GTexel/s |
| 82.6 TFLOPS | FLOPS (FP32) | 1.3-1.8 TFLOPS |
| GDDR6X | Memory Type | System Shared |
| 24 GB | Memory Size | System RAM Dependent |
| 2625 MHz | Memory Clock | System RAM Dependent |
| 21000 Mbps | Effective Memory Speed | System RAM Dependent |
| 384-bit | Bus | — |
| No | ECC | No |
| 1010 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | IGP |
| 450 W | TGP | 10-45 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 7 nm |
| 609 mm² | Die Size | — |
| 76.3 billion | Transistor Count | — |
| 125.29 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.1 |
| 1.3 | Vulkan | — |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| September 20, 2022 | Released | January 7, 2020 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Ada Lovelace | Architecture | Raven |
| AD102 | GPU Codename | — |
| -Intel Core i9 14900Kor above | Recommended CPU | -AMD Ryzen 5 5500Uor above |
| 42169 | Steel Nomad Lite Score | 943 |
| 36311 | Time Spy | 1068 |
| 187386 | Solar Bay | — |
| 26128 | Port Royal | — |
| 72387 | Fire Strike | 3396 |
| 85230 | Wild Life Extreme | 2015 |
| 195880 | Night Raid | 13093 |
| 2235 MHz | Base Clock | 300 MHz |
| 2520 MHz | Boost Clock | 1500-2000 MHz (configurable) |
| 16384 | Shading Units | 448 |
| 512 | Texture Mapping Units (TMUs) | 28 |
| 176 | Render Output Units (ROPs) | 8 |
| 128 | Compute Units (Pipelines) | 7 |
| 512 | Tensor Cores | No |
| 128 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 72MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |