Quick/Comparisons
The Radeon RX 7900 XT takes the lead in gaming performance with a score of 72, outpacing the GeForce RTX 3090's 61.
Both the GeForce RTX 3090 and Radeon RX 7900 XT deliver solid workstation performance, with the Radeon RX 7900 XT edging out the GeForce RTX 3090 by a single point.
The Radeon RX 7900 XT excels in AI/ML tasks with a score of 68, leaving the GeForce RTX 3090's 53 behind.
61 | Gaming | 72 |
69 | Workstation | 70 |
53 | AI/ML | 68 |
35 | Energy Efficiency | 45 |
62 | Quick Comparison Final Score | 70 |
| GA102 | Graphics Processor | Navi 31 |
| 10496 | Cores | 5376 |
| 328 / 112 | TMUs / ROPs | 336 / 192 |
| 5800.59 | Blender GPU | 3548.59 |
| 125 | Forza Horizon 5 | 157 |
| 175 | The Witcher 3 | 228 |
| 212 | Counter-Strike 2 | 223 |
| 142 | Far Cry 6 | 173 |
| 106 | Hogwarts Legacy | 126 |
| 159 | Call of Duty | 222 |
| 97 | Ghost of Tsushima | 129 |
| 132 | Cyberpunk 2077 | 158 |
| 226 | Tomb Raider | 247 |
| 153 | Average FPS | 185 |
| 179 | 1080p High | 219 |
| 153 | 1080p Ultra | 185 |
| 119 | 1440p Ultra | 144 |
| 70 | 4K Ultra | 85 |
| Low | Margin of Error | Low |
| 211669 | GB6 Compute Score | 203754 |
| 320.8 img/sec | Background Blur | 419.8 img/sec |
| 207.2 img/sec | Face Detection | 240.5 img/sec |
| 10.1 Gpixels/sec | Horizon Detection | 8.72 Gpixels/sec |
| 14.4 Gpixels/sec | Edge Detection | 12 Gpixels/sec |
| 11.5 Gpixels/sec | Gaussian Blur | 9.88 Gpixels/sec |
| 1.48 Gpixels/sec | Feature Matching | 1.71 Gpixels/sec |
| 984.2 Gpixels/sec | Stereo Matching | 701.7 Gpixels/sec |
| 27764.9 FPS | Particle Physics | 26631.4 FPS |
| OpenCL | API | OpenCL |
| 26551 | G3D Mark Score | 29015 |
| 1069 | G2D Mark | 1241 |
| 218 FPS | DirectX 11 | 340 FPS |
| 110 FPS | DirectX 12 | 111 FPS |
| 15117 Ops/s | GPU Compute | 16851 Ops/s |
| 27237 | GB6 ML Single Precision | 39099 |
| 41500 | GB6 ML Half Precision | 47298 |
| 15927 | GB6 ML Quantized | 30875 |
| 10665 | Image Classification (SP) | 16951 |
| 28963 | Image Segmentation (HP) | 23234 |
| 22697 | Image Super Resolution (Q) | 41128 |
| 55232 | Face Detection (HP) | 67615 |
| 128155 | Pose Estimation (Q) | 237026 |
| 3152 | Text Classification (SP) | 4961 |
| 5088 | Machine Translation (HP) | 7043 |
| 13891 | Object Detection (SP) | 18737 |
| 37984 | Depth Estimation (Q) | 67746 |
| 272000 | Style Transfer (SP) | 457919 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 190 GPixel/s | Pixel Fill Rate | 460 GPixel/s |
| 556 GTexel/s | Texture Fill Rate | 804 GTexel/s |
| 35.6 TFLOPS | FLOPS (FP32) | 51.5 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 24 GB | Memory Size | 20 GB |
| 1219 MHz | Memory Clock | 2500 MHz |
| 19500 Mbps | Effective Memory Speed | 20000 Mbps |
| 384-bit | Bus | 320-bit |
| No | ECC | No |
| 936.2 GB/s | Memory Bandwidth | 800 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 350 W | TGP | 300 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | 529 mm² |
| 28 billion | Transistor Count | 57 billion |
| 44.59 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.6 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| September 24, 2020 | Released | December 13, 2023 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | RDNA 3.0 |
| GA102 | GPU Codename | Navi 31 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 21851 | Steel Nomad Lite Score | 24675 |
| 19896 | Time Spy | 27067 |
| 97375 | Solar Bay | 104912 |
| 13631 | Port Royal | 14358 |
| 47515 | Fire Strike | 67256 |
| 43673 | Wild Life Extreme | 48319 |
| 139755 | Night Raid | 176267 |
| 1395 MHz | Base Clock | 1387 MHz |
| 1695 MHz | Boost Clock | 2394 MHz |
| 10496 | Shading Units | 5376 |
| 328 | Texture Mapping Units (TMUs) | 336 |
| 112 | Render Output Units (ROPs) | 192 |
| 82 | Compute Units (Pipelines) | — |
| 328 | Tensor Cores | — |
| 82 | Ray-tracing Cores | 84 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 6MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare GeForce RTX 3090 with another →