Quick/Comparisons
32 | Gaming | 13 |
39 | Workstation | 22 |
33 | AI/ML |
Compare with something else?
Compare GeForce RTX 2070 with another →12 |
27 | Energy Efficiency | 32 |
34 | Quick Comparison Final Score | 16 |
| TU104 | Graphics Processor | Polaris 20 |
| 2560 | Cores | 2048 |
| 160 / 64 | TMUs / ROPs | 128 / 32 |
| 2361.66 | Blender GPU | 329.21 |
| 77 | Forza Horizon 5 | 36 |
| 109 | The Witcher 3 | 34 |
| 150 | Counter-Strike 2 | 43 |
| 91 | Far Cry 6 | 40 |
| 61 | Hogwarts Legacy | 22 |
| 82 | Call of Duty | 36 |
| 58 | Ghost of Tsushima | 21 |
| 71 | Cyberpunk 2077 | 26 |
| 113 | Tomb Raider | 42 |
| 90 | Average FPS | 33 |
| 111 | 1080p High | 45 |
| 90 | 1080p Ultra | 33 |
| 66 | 1440p Ultra | 23 |
| 38 | 4K Ultra | 12 |
| Low | Margin of Error | Low |
| 105349 | GB6 Compute Score | 37147 |
| 166.7 img/sec | Background Blur | 55.7 img/sec |
| 103.3 img/sec | Face Detection | 31.3 img/sec |
| 4.21 Gpixels/sec | Horizon Detection | 1.41 Gpixels/sec |
| 5.56 Gpixels/sec | Edge Detection | 2.82 Gpixels/sec |
| 5.58 Gpixels/sec | Gaussian Blur | 2.57 Gpixels/sec |
| 1.17 Gpixels/sec | Feature Matching | 0.31 Gpixels/sec |
| 489.7 Gpixels/sec | Stereo Matching | 143.2 Gpixels/sec |
| 13242.9 FPS | Particle Physics | 5080.1 FPS |
| OpenCL | API | OpenCL |
| 18141 | G3D Mark Score | 7922 |
| 878 | G2D Mark | 724 |
| 153 FPS | DirectX 11 | 55 FPS |
| 67 FPS | DirectX 12 | 39 FPS |
| 7473 Ops/s | GPU Compute | 2890 Ops/s |
| 16276 | GB6 ML Single Precision | 6885 |
| 27406 | GB6 ML Half Precision | 7446 |
| 10983 | GB6 ML Quantized | 4931 |
| 6648 | Image Classification (SP) | 2676 |
| 16442 | Image Segmentation (HP) | 3757 |
| 15383 | Image Super Resolution (Q) | 6179 |
| 32861 | Face Detection (HP) | 10752 |
| 66348 | Pose Estimation (Q) | 35488 |
| 2166 | Text Classification (SP) | 1051 |
| 4239 | Machine Translation (HP) | 1933 |
| 8194 | Object Detection (SP) | 3048 |
| 26192 | Depth Estimation (Q) | 12040 |
| 137642 | Style Transfer (SP) | 71201 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 113 GPixel/s | Pixel Fill Rate | 40 GPixel/s |
| 283 GTexel/s | Texture Fill Rate | 159 GTexel/s |
| 9.1 TFLOPS | FLOPS (FP32) | 5.1 TFLOPS |
| GDDR6 | Memory Type | GDDR5 |
| 8 GB | Memory Size | 4 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 14000 Mbps | Effective Memory Speed | 7000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 224 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 3.0 x16 |
| 215 W | TGP | 150 W |
| TSMC | Manufacturing | GlobalFoundries |
| 12 nm | Fabrication Process | 14 nm |
| 545 mm² | Die Size | 232 mm² |
| 13 billion | Transistor Count | 5 billion |
| 23.85 MTr/mm² | Transistor Density | 21.55 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 7.5 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| July 9, 2019 | Released | April 18, 2017 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Turing | Architecture | GCN 4.0 |
| TU104 | GPU Codename | Polaris 20 |
| -Intel Core i7 9700Kor above | Recommended CPU | -Intel Core i5 8500or above |
| 10053 | Steel Nomad Lite Score | 3702 |
| 10167 | Time Spy | 3855 |
| 45871 | Solar Bay | — |
| 6032 | Port Royal | — |
| 25675 | Fire Strike | 13443 |
| 20745 | Wild Life Extreme | 7941 |
| 102728 | Night Raid | 50379 |
| 1605 MHz | Base Clock | 1168 MHz |
| 1770 MHz | Boost Clock | 1244 MHz |
| 2560 | Shading Units | 2048 |
| 160 | Texture Mapping Units (TMUs) | 128 |
| 64 | Render Output Units (ROPs) | 32 |
| 40 | Compute Units (Pipelines) | — |
| 320 | Tensor Cores | No |
| 40 | Ray-tracing Cores | No |
| 64KB per cluster | L1 Cache | 16KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |