Quick/Comparisons
21 | Gaming | 5 |
29 | Workstation | 11 |
22 | AI/ML |
Compare with something else?
Compare GeForce RTX 2060 with another →4 |
46 | Energy Efficiency | 89 |
27 | Quick Comparison Final Score | 20 |
| TU106 (N18E-G1-B) | Graphics Processor | Raphael |
| 1920 | Cores | 128 |
| 120 / 48 | TMUs / ROPs | 8 / 4 |
| 1387.02 | Blender GPU | — |
| 49 | Forza Horizon 5 | — |
| 66 | The Witcher 3 | — |
| 91 | Counter-Strike 2 | — |
| 61 | Far Cry 6 | — |
| 34 | Hogwarts Legacy | — |
| 46 | Call of Duty | — |
| 32 | Ghost of Tsushima | — |
| 43 | Cyberpunk 2077 | — |
| 71 | Tomb Raider | — |
| 55 | Average FPS | — |
| 72 | 1080p High | — |
| 55 | 1080p Ultra | — |
| 39 | 1440p Ultra | — |
| 20 | 4K Ultra | — |
| Low | Margin of Error | — |
| 73982 | GB6 Compute Score | 6272 |
| 150.7 img/sec | Background Blur | 13.4 img/sec |
| 75.5 img/sec | Face Detection | 8.66 img/sec |
| 2.83 Gpixels/sec | Horizon Detection | 0.23 Gpixels/sec |
| 3.68 Gpixels/sec | Edge Detection | 0.32 Gpixels/sec |
| 4.08 Gpixels/sec | Gaussian Blur | 0.2 Gpixels/sec |
| 0.89 Gpixels/sec | Feature Matching | 0.08 Gpixels/sec |
| 257.7 Gpixels/sec | Stereo Matching | 24.2 Gpixels/sec |
| 9069.6 FPS | Particle Physics | 827 FPS |
| OpenCL | API | OpenCL |
| 11353 | G3D Mark Score | 1757 |
| 540 | G2D Mark | 516 |
| 96 FPS | DirectX 11 | 15 FPS |
| 39 FPS | DirectX 12 | 7 FPS |
| 3992 Ops/s | GPU Compute | 1128 Ops/s |
| 10073 | GB6 ML Single Precision | 1965 |
| 17250 | GB6 ML Half Precision | 2172 |
| 7165 | GB6 ML Quantized | 1610 |
| 4450 | Image Classification (SP) | 679 |
| 9120 | Image Segmentation (HP) | 642 |
| 9180 | Image Super Resolution (Q) | 2131 |
| 18866 | Face Detection (HP) | 2204 |
| 41027 | Pose Estimation (Q) | 5478 |
| 1741 | Text Classification (SP) | 728 |
| 2269 | Machine Translation (HP) | 1231 |
| 4980 | Object Detection (SP) | 729 |
| 18044 | Depth Estimation (Q) | 3337 |
| 91554 | Style Transfer (SP) | 11335 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 56-58 GPixel/s | Pixel Fill Rate | 9 GPixel/s |
| 141-144 GTexel/s | Texture Fill Rate | 18 GTexel/s |
| 4.5-4.6 TFLOPS | FLOPS (FP32) | 0.6 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 6 GB | Memory Size | — |
| 1375 MHz | Memory Clock | — |
| 11000 Mbps | Effective Memory Speed | — |
| 192-bit | Bus | — |
| No | ECC | No |
| 264 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x8 |
| 80-115 W (configurable) | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 6 nm |
| 445 mm² | Die Size | 122 mm² |
| 10.8 billion | Transistor Count | 3.4 billion |
| 24.27 MTr/mm² | Transistor Density | 27.87 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 2 |
| 7.5 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4 | DisplayPort | — |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Turing | Architecture | RDNA 2.0 |
| TU106 (N18E-G1-B) | GPU Codename | Raphael |
| -Intel Core i7 10750Hor above | Recommended CPU | -AMD Ryzen 5 7600or above |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 29, 2019 | Released | October 1, 2022 |
| 5764 | Steel Nomad Lite Score | 616 |
| 5959 | Time Spy | 711 |
| 25775 | Solar Bay | 2913 |
| 3328 | Port Royal | 332 |
| 15850 | Fire Strike | 2417 |
| 11601 | Wild Life Extreme | 1402 |
| 62117 | Night Raid | 10038 |
| 960 MHz | Base Clock | 400 MHz |
| 1175-1200 MHz (configurable) | Boost Clock | 2200 MHz |
| 1920 | Shading Units | 128 |
| 120 | Texture Mapping Units (TMUs) | 8 |
| 48 | Render Output Units (ROPs) | 4 |
| 30 | Compute Units (Pipelines) | 2 |
| 240 | Tensor Cores | — |
| 30 | Ray-tracing Cores | 2 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 3MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |