Quick/Comparisons
92 | Gaming | 31 |
91 | Workstation | 35 |
76 | AI/ML |
Compare with something else?
Compare GeForce RTX 4090 with another →29 |
43 | Energy Efficiency | 67 |
89 | Quick Comparison Final Score | 38 |
| AD102 | Graphics Processor | GB207 |
| 16384 | Cores | 2560 |
| 512 / 176 | TMUs / ROPs | 80 / 32 |
| 11688.48 | Blender GPU | 2952.19 |
| 203 | Forza Horizon 5 | 68 |
| 270 | The Witcher 3 | 98 |
| 245 | Counter-Strike 2 | 133 |
| 183 | Far Cry 6 | 81 |
| 165 | Hogwarts Legacy | 56 |
| 269 | Call of Duty | 71 |
| 150 | Ghost of Tsushima | 49 |
| 204 | Cyberpunk 2077 | 63 |
| 283 | Tomb Raider | 95 |
| 219 | Average FPS | 79 |
| 256 | 1080p High | 99 |
| 219 | 1080p Ultra | 79 |
| 176 | 1440p Ultra | 57 |
| 107 | 4K Ultra | 31 |
| Low | Margin of Error | Low |
| 2.38 Gpixels/sec | Feature Matching | 1.07 Gpixels/sec |
| 1950 Gpixels/sec | Stereo Matching | 414.3 Gpixels/sec |
| 48090.4 FPS | Particle Physics | 13519.1 FPS |
| OpenCL | API | OpenCL |
| 316301 | GB6 Compute Score | 91033 |
| 318.9 img/sec | Background Blur | 154.5 img/sec |
| 222.8 img/sec | Face Detection | 94.6 img/sec |
| 14.2 Gpixels/sec | Horizon Detection | 3.36 Gpixels/sec |
| 21 Gpixels/sec | Edge Detection | 4.21 Gpixels/sec |
| 23.9 Gpixels/sec | Gaussian Blur | 4.26 Gpixels/sec |
| 38071 | G3D Mark Score | 14357 |
| 1303 | G2D Mark | 760 |
| 324 FPS | DirectX 11 | 128 FPS |
| 151 FPS | DirectX 12 | 67 FPS |
| 26193 Ops/s | GPU Compute | 5169 Ops/s |
| 42962 | GB6 ML Single Precision | 16186 |
| 59636 | GB6 ML Half Precision | 31589 |
| 31670 | GB6 ML Quantized | 13082 |
| 15600 | Image Classification (SP) | 6724 |
| 36657 | Image Segmentation (HP) | 20455 |
| 48114 | Image Super Resolution (Q) | 17332 |
| 78111 | Face Detection (HP) | 37078 |
| 289639 | Pose Estimation (Q) | 68680 |
| 4074 | Text Classification (SP) | 2764 |
| 6349 | Machine Translation (HP) | 5076 |
| 21186 | Object Detection (SP) | 8520 |
| 75599 | Depth Estimation (Q) | 32304 |
| 601428 | Style Transfer (SP) | 110367 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 444 GPixel/s | Pixel Fill Rate | 48-85 GPixel/s |
| 1290 GTexel/s | Texture Fill Rate | 120-213 GTexel/s |
| 82.6 TFLOPS | FLOPS (FP32) | 7.7-13.6 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 24 GB | Memory Size | 8 GB |
| 2625 MHz | Memory Clock | 1750 MHz |
| 21000 Mbps | Effective Memory Speed | 24000 Mbps |
| 384-bit | Bus | 128-bit |
| No | ECC | No |
| 1010 GB/s | Memory Bandwidth | 384 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 450 W | TGP | 35-115 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 609 mm² | Die Size | 149 mm² |
| 76.3 billion | Transistor Count | 16.9 billion |
| 125.29 MTr/mm² | Transistor Density | 113.42 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| September 20, 2022 | Released | June 24, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Ada Lovelace | Architecture | Blackwell 2.0 |
| AD102 | GPU Codename | GB207 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core Ultra 5 245HXor above |
| 42169 | Steel Nomad Lite Score | 9532 |
| 36311 | Time Spy | 9528 |
| 187386 | Solar Bay | 42379 |
| 26128 | Port Royal | 5774 |
| 72387 | Fire Strike | 25853 |
| 85230 | Wild Life Extreme | 17822 |
| 195880 | Night Raid | 90582 |
| 2235 MHz | Base Clock | 1020-1500 MHz (configurable) |
| 2520 MHz | Boost Clock | 1500-2662 MHz (configurable) |
| 16384 | Shading Units | 2560 |
| 512 | Texture Mapping Units (TMUs) | 80 |
| 176 | Render Output Units (ROPs) | 32 |
| 128 | Compute Units (Pipelines) | 20 |
| 512 | Tensor Cores | 80 |
| 128 | Ray-tracing Cores | 20 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 72MB shared | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |