Quick/Comparisons
25 | Gaming | 44 |
35 | Workstation | 48 |
24 | AI/ML |
Compare with something else?
Compare GeForce RTX 2070 with another →39 |
46 | Energy Efficiency | 27 |
31 | Quick Comparison Final Score | 44 |
| TU106B | Graphics Processor | TU102 |
| 2304 | Cores | 4352 |
| 144 / 64 | TMUs / ROPs | 272 / 88 |
| 1823.68 | Blender GPU | 3046.64 |
| 61 | Forza Horizon 5 | 101 |
| 84 | The Witcher 3 | 144 |
| 117 | Counter-Strike 2 | 199 |
| 74 | Far Cry 6 | 122 |
| 45 | Hogwarts Legacy | 82 |
| 61 | Call of Duty | 118 |
| 42 | Ghost of Tsushima | 78 |
| 53 | Cyberpunk 2077 | 98 |
| 84 | Tomb Raider | 155 |
| 69 | Average FPS | 122 |
| 87 | 1080p High | 145 |
| 69 | 1080p Ultra | 122 |
| 49 | 1440p Ultra | 92 |
| 26 | 4K Ultra | 52 |
| Low | Margin of Error | Low |
| 92843 | GB6 Compute Score | 144745 |
| 159 img/sec | Background Blur | 211 img/sec |
| 91.2 img/sec | Face Detection | 141.3 img/sec |
| 3.67 Gpixels/sec | Horizon Detection | 6.24 Gpixels/sec |
| 5.1 Gpixels/sec | Edge Detection | 8.1 Gpixels/sec |
| 5.03 Gpixels/sec | Gaussian Blur | 9.22 Gpixels/sec |
| 1.08 Gpixels/sec | Feature Matching | 1.46 Gpixels/sec |
| 411.9 Gpixels/sec | Stereo Matching | 627.3 Gpixels/sec |
| 10180.5 FPS | Particle Physics | 16980.5 FPS |
| OpenCL | API | OpenCL |
| 12357 | G3D Mark Score | 21477 |
| 602 | G2D Mark | 927 |
| 111 FPS | DirectX 11 | 192 FPS |
| 41 FPS | DirectX 12 | 83 FPS |
| 4490 Ops/s | GPU Compute | 9906 Ops/s |
| 10388 | GB6 ML Single Precision | 19878 |
| 17021 | GB6 ML Half Precision | 31237 |
| 7357 | GB6 ML Quantized | 12663 |
| 3954 | Image Classification (SP) | 8213 |
| 9425 | Image Segmentation (HP) | 19891 |
| 11209 | Image Super Resolution (Q) | 17598 |
| 18147 | Face Detection (HP) | 39785 |
| 47333 | Pose Estimation (Q) | 84003 |
| 1546 | Text Classification (SP) | 2062 |
| 2209 | Machine Translation (HP) | 4192 |
| 4976 | Object Detection (SP) | 10444 |
| 18466 | Depth Estimation (Q) | 31856 |
| 90152 | Style Transfer (SP) | 207773 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 92-95 GPixel/s | Pixel Fill Rate | 136 GPixel/s |
| 207-214 GTexel/s | Texture Fill Rate | 420 GTexel/s |
| 6.6-6.8 TFLOPS | FLOPS (FP32) | 13.4 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 11 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 14000 Mbps | Effective Memory Speed | 14000 Mbps |
| 256-bit | Bus | 352-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 616 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 3.0 x16 |
| 115 W | TGP | 250 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 12 nm |
| 445 mm² | Die Size | 754 mm² |
| 10.8 billion | Transistor Count | 18 billion |
| 24.27 MTr/mm² | Transistor Density | 23.87 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 7.5 | CUDA | 7.5 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 2 |
| 1.4 | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 29, 2019 | Released | September 27, 2018 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Turing | Architecture | Turing |
| TU106B | GPU Codename | TU102 |
| -Intel Core i7 10750Hor above | Recommended CPU | -Intel Core i9 9900Kor above |
| 7234 | Steel Nomad Lite Score | 14284 |
| 7566 | Time Spy | 14656 |
| 31700 | Solar Bay | 64076 |
| 4446 | Port Royal | 9109 |
| 19887 | Fire Strike | 35666 |
| 14527 | Wild Life Extreme | 29554 |
| 65976 | Night Raid | 115500 |
| 1215-1305 MHz (configurable) | Base Clock | 1350 MHz |
| 1440-1485 MHz (configurable) | Boost Clock | 1545 MHz |
| 2304 | Shading Units | 4352 |
| 144 | Texture Mapping Units (TMUs) | 272 |
| 64 | Render Output Units (ROPs) | 88 |
| 36 | Compute Units (Pipelines) | 68 |
| 288 | Tensor Cores | 544 |
| 36 | Ray-tracing Cores | 68 |
| 64KB per cluster | L1 Cache | 64KB per cluster |
| 4MB shared | L2 Cache | 5632KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |