Quick/Comparisons
The Nvidia RTX 5000 Ada dominates in gaming performance, thanks to its significantly higher score of 73. Its strong performance makes it the clear winner in this use case.
The Nvidia RTX 5000 Ada takes the lead in content creation, boasting a score of 82, which is 45 points higher than the GeForce RTX 3060's score of 37.
The Nvidia RTX 5000 Ada edges out the GeForce RTX 3060 in AI/ML performance, with a score of 54, which is 25 points higher than the GeForce RTX 3060's score of 29.
31 | Gaming | 73 |
37 | Workstation | 82 |
29 | AI/ML | 54 |
37 | Energy Efficiency | 45 |
33 | Quick Comparison Final Score | 73 |
| GA106 | Graphics Processor | AD102 |
| 3584 | Cores | 12800 |
| 112 / 48 | TMUs / ROPs | 400 / 176 |
| 2303.56 | Blender GPU | 7348.98 |
| 71 | Forza Horizon 5 | 146 |
| 100 | The Witcher 3 | 186 |
| 133 | Counter-Strike 2 | 213 |
| 83 | Far Cry 6 | 151 |
| 56 | Hogwarts Legacy | 117 |
| 73 | Call of Duty | 179 |
| 49 | Ghost of Tsushima | 108 |
| 62 | Cyberpunk 2077 | 148 |
| 97 | Tomb Raider | 242 |
| 80 | Average FPS | 166 |
| 100 | 1080p High | 196 |
| 80 | 1080p Ultra | 166 |
| 59 | 1440p Ultra | 132 |
| 32 | 4K Ultra | 78 |
| Low | Margin of Error | High |
| 91603 | GB6 Compute Score | 260099 |
| 149.6 img/sec | Background Blur | 286.6 img/sec |
| 91 img/sec | Face Detection | 220.4 img/sec |
| 4.07 Gpixels/sec | Horizon Detection | 9.93 Gpixels/sec |
| 5.58 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 3.92 Gpixels/sec | Gaussian Blur | 18.9 Gpixels/sec |
| 1.01 Gpixels/sec | Feature Matching | 2.2 Gpixels/sec |
| 372.9 Gpixels/sec | Stereo Matching | 1580 Gpixels/sec |
| 12226.3 FPS | Particle Physics | 41235.6 FPS |
| OpenCL | API | OpenCL |
| 16744 | G3D Mark Score | 30196 |
| 966 | G2D Mark | 998 |
| 128 FPS | DirectX 11 | 273 FPS |
| 69 FPS | DirectX 12 | 106 FPS |
| 8266 Ops/s | GPU Compute | 20736 Ops/s |
| 15123 | GB6 ML Single Precision | 24715 |
| 25942 | GB6 ML Half Precision | 36753 |
| 10356 | GB6 ML Quantized | 19649 |
| 6645 | Image Classification (SP) | 9943 |
| 15338 | Image Segmentation (HP) | 19696 |
| 14283 | Image Super Resolution (Q) | 32252 |
| 28862 | Face Detection (HP) | 43098 |
| 61313 | Pose Estimation (Q) | 138689 |
| 2463 | Text Classification (SP) | 2893 |
| 3793 | Machine Translation (HP) | 4064 |
| 7712 | Object Detection (SP) | 12467 |
| 25461 | Depth Estimation (Q) | 50352 |
| 123233 | Style Transfer (SP) | 265482 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 85 GPixel/s | Pixel Fill Rate | 449 GPixel/s |
| 199 GTexel/s | Texture Fill Rate | 1020 GTexel/s |
| 12.7 TFLOPS | FLOPS (FP32) | 65.3 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 12 GB | Memory Size | 32 GB |
| 1875 MHz | Memory Clock | 2250 MHz |
| 15000 Mbps | Effective Memory Speed | 18000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 360 GB/s | Memory Bandwidth | 576 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 170 W | TGP | 250 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 276 mm² | Die Size | 609 mm² |
| 12 billion | Transistor Count | 76 billion |
| 43.48 MTr/mm² | Transistor Density | 124.79 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 12, 2021 | Released | August 9, 2023 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA106 | GPU Codename | AD102 |
| -Intel Core i5 12600Kor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 9002 | Steel Nomad Lite Score | 29190 |
| 8754 | Time Spy | 18675 |
| 41139 | Solar Bay | 128428 |
| 5145 | Port Royal | 17754 |
| 22306 | Fire Strike | 62027 |
| 17726 | Wild Life Extreme | 52866 |
| 97592 | Night Raid | 210443 |
| 1320 MHz | Base Clock | 1155 MHz |
| 1777 MHz | Boost Clock | 2550 MHz |
| 3584 | Shading Units | 12800 |
| 112 | Texture Mapping Units (TMUs) | 400 |
| 48 | Render Output Units (ROPs) | 176 |
| 28 | Compute Units (Pipelines) | 100 |
| 112 | Tensor Cores | 400 |
| 28 | Ray-tracing Cores | 100 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 3MB shared | L2 Cache | 72MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 3060 with another →