Quick/Comparisons
The GeForce RTX 5080 outperforms the GeForce RTX 3060 by a significant margin of 56 points, thanks to its superior architecture and higher memory capacity. Its 87 score is a testament to its exceptional gaming capabilities.
Although the GeForce RTX 3060 holds a slight edge in workstation performance, the GeForce RTX 5080's overall score of 85 is still significantly higher, thanks to its strong performance in multiple areas. Its 16GB GDDR7 memory also provides a notable advantage.
The GeForce RTX 5080's AI/ML compute capabilities are superior to the GeForce RTX 3060's, with a 41-point difference in scores. Its Blackwell 2.0 architecture and 16GB GDDR7 memory contribute to its strong performance in this area.
31 | Gaming | 87 |
37 | Workstation | 85 |
29 | AI/ML | 70 |
37 | Energy Efficiency | 49 |
33 | Quick Comparison Final Score | 84 |
| GA106 | Graphics Processor | GB203-400 |
| 3584 | Cores | 10752 |
| 112 / 48 | TMUs / ROPs | 336 / 112 |
| 2303.56 | Blender GPU | 9138.54 |
| 71 | Forza Horizon 5 | 185 |
| 100 | The Witcher 3 | 237 |
| 133 | Counter-Strike 2 | 237 |
| 83 | Far Cry 6 | 176 |
| 56 | Hogwarts Legacy | 154 |
| 73 | Call of Duty | 241 |
| 49 | Ghost of Tsushima | 137 |
| 62 | Cyberpunk 2077 | 190 |
| 97 | Tomb Raider | 270 |
| 80 | Average FPS | 203 |
| 100 | 1080p High | 239 |
| 80 | 1080p Ultra | 203 |
| 59 | 1440p Ultra | 164 |
| 32 | 4K Ultra | 97 |
| Low | Margin of Error | Low |
| 91603 | GB6 Compute Score | 297747 |
| 149.6 img/sec | Background Blur | 319.6 img/sec |
| 91 img/sec | Face Detection | 225 img/sec |
| 4.07 Gpixels/sec | Horizon Detection | 13.6 Gpixels/sec |
| 5.58 Gpixels/sec | Edge Detection | 19.5 Gpixels/sec |
| 3.92 Gpixels/sec | Gaussian Blur | 20.4 Gpixels/sec |
| 1.01 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 372.9 Gpixels/sec | Stereo Matching | 1750 Gpixels/sec |
| 12226.3 FPS | Particle Physics | 43676.6 FPS |
| OpenCL | API | OpenCL |
| 16744 | G3D Mark Score | 35695 |
| 966 | G2D Mark | 1407 |
| 128 FPS | DirectX 11 | 327 FPS |
| 69 FPS | DirectX 12 | 144 FPS |
| 8266 Ops/s | GPU Compute | 19397 Ops/s |
| 15123 | GB6 ML Single Precision | 38994 |
| 25942 | GB6 ML Half Precision | 66609 |
| 10356 | GB6 ML Quantized | 29206 |
| 6645 | Image Classification (SP) | 15441 |
| 15338 | Image Segmentation (HP) | 47173 |
| 14283 | Image Super Resolution (Q) | 43223 |
| 28862 | Face Detection (HP) | 92863 |
| 61313 | Pose Estimation (Q) | 202202 |
| 2463 | Text Classification (SP) | 3701 |
| 3793 | Machine Translation (HP) | 7905 |
| 7712 | Object Detection (SP) | 20955 |
| 25461 | Depth Estimation (Q) | 69068 |
| 123233 | Style Transfer (SP) | 349205 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 85 GPixel/s | Pixel Fill Rate | 293 GPixel/s |
| 199 GTexel/s | Texture Fill Rate | 879 GTexel/s |
| 12.7 TFLOPS | FLOPS (FP32) | 56.3 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 12 GB | Memory Size | 16 GB |
| 1875 MHz | Memory Clock | 1875 MHz |
| 15000 Mbps | Effective Memory Speed | 30000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 360 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 170 W | TGP | 360 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 276 mm² | Die Size | 378 mm² |
| 12 billion | Transistor Count | 45.6 billion |
| 43.48 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 12, 2021 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA106 | GPU Codename | GB203-400 |
| -Intel Core i5 12600Kor above | Recommended CPU | -Intel Core Ultra 7 265Kor above |
| 9002 | Steel Nomad Lite Score | 36200 |
| 8754 | Time Spy | 32989 |
| 41139 | Solar Bay | 160901 |
| 5145 | Port Royal | 23257 |
| 22306 | Fire Strike | 75518 |
| 17726 | Wild Life Extreme | 69544 |
| 97592 | Night Raid | 200077 |
| 1320 MHz | Base Clock | 2295 MHz |
| 1777 MHz | Boost Clock | 2617 MHz |
| 3584 | Shading Units | 10752 |
| 112 | Texture Mapping Units (TMUs) | 336 |
| 48 | Render Output Units (ROPs) | 112 |
| 28 | Compute Units (Pipelines) | 84 |
| 112 | Tensor Cores | 336 |
| 28 | Ray-tracing Cores | 84 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 3MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 3060 with another →