Quick/Comparisons
22 | Gaming | 45 |
28 | Workstation | 47 |
16 | AI/ML |
Compare with something else?
Compare GeForce GTX 1070 with another →44 |
20 | Energy Efficiency | 36 |
23 | Quick Comparison Final Score | 45 |
| GP104 | Graphics Processor | Navi 21 |
| 2432 | Cores | 3840 |
| 152 / 64 | TMUs / ROPs | 240 / 96 |
| 629.59 | Blender GPU | 1894.91 |
| 55 | Forza Horizon 5 | 116 |
| 77 | The Witcher 3 | 152 |
| 108 | Counter-Strike 2 | 186 |
| 70 | Far Cry 6 | 125 |
| 42 | Hogwarts Legacy | 88 |
| 53 | Call of Duty | 134 |
| 39 | Ghost of Tsushima | 90 |
| 45 | Cyberpunk 2077 | 98 |
| 80 | Tomb Raider | 168 |
| 63 | Average FPS | 129 |
| 79 | 1080p High | 157 |
| 63 | 1080p Ultra | 129 |
| 45 | 1440p Ultra | 95 |
| 24 | 4K Ultra | 55 |
| Low | Margin of Error | Low |
| 57735 | GB6 Compute Score | 135060 |
| 149.2 img/sec | Background Blur | 298.6 img/sec |
| 67.6 img/sec | Face Detection | 186.2 img/sec |
| 2.36 Gpixels/sec | Horizon Detection | 4.75 Gpixels/sec |
| 3.57 Gpixels/sec | Edge Detection | 6.68 Gpixels/sec |
| 4.32 Gpixels/sec | Gaussian Blur | 5.58 Gpixels/sec |
| 0.27 Gpixels/sec | Feature Matching | 1.16 Gpixels/sec |
| 209.6 Gpixels/sec | Stereo Matching | 579 Gpixels/sec |
| 6584.9 FPS | Particle Physics | 18755.1 FPS |
| OpenCL | API | OpenCL |
| 14658 | G3D Mark Score | 22023 |
| 876 | G2D Mark | 998 |
| 107 FPS | DirectX 11 | 212 FPS |
| 52 FPS | DirectX 12 | 89 FPS |
| 7162 Ops/s | GPU Compute | 10764 Ops/s |
| 8949 | GB6 ML Single Precision | 25097 |
| 8769 | GB6 ML Half Precision | 27988 |
| 6546 | GB6 ML Quantized | 19116 |
| 3473 | Image Classification (SP) | 11245 |
| 5149 | Image Segmentation (HP) | 13617 |
| 9722 | Image Super Resolution (Q) | 27747 |
| 9306 | Face Detection (HP) | 38124 |
| 34870 | Pose Estimation (Q) | 119493 |
| 2139 | Text Classification (SP) | 2425 |
| 2424 | Machine Translation (HP) | 5228 |
| 4566 | Object Detection (SP) | 11986 |
| 14316 | Depth Estimation (Q) | 46083 |
| 88984 | Style Transfer (SP) | 281860 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 108 GPixel/s | Pixel Fill Rate | 202 GPixel/s |
| 256 GTexel/s | Texture Fill Rate | 505 GTexel/s |
| 8.2 TFLOPS | FLOPS (FP32) | 16.2 TFLOPS |
| GDDR5 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 16 GB |
| 2002 MHz | Memory Clock | 2000 MHz |
| 8000 Mbps | Effective Memory Speed | 16000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 256.3 GB/s | Memory Bandwidth | 512 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x16 |
| 180 W | TGP | 250 W |
| TSMC | Manufacturing | TSMC |
| 16 nm | Fabrication Process | 7 nm |
| 314 mm² | Die Size | 520 mm² |
| 7 billion | Transistor Count | 26 billion |
| 22.29 MTr/mm² | Transistor Density | 50 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 6.1 | CUDA | — |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| November 2, 2017 | Released | October 28, 2020 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Pascal | Architecture | RDNA 2.0 |
| GP104 | GPU Codename | Navi 21 |
| -Intel Core i7 7700Kor above | Recommended CPU | -Intel Core i5 12600or above |
| 6671 | Steel Nomad Lite Score | 14548 |
| 6843 | Time Spy | 16220 |
| 18267 | Solar Bay | 64755 |
| 1552 | Port Royal | 8137 |
| 20115 | Fire Strike | 44377 |
| 13248 | Wild Life Extreme | 29764 |
| 78890 | Night Raid | 142721 |
| 1607 MHz | Base Clock | 1700 MHz |
| 1683 MHz | Boost Clock | 2105 MHz |
| 2432 | Shading Units | 3840 |
| 152 | Texture Mapping Units (TMUs) | 240 |
| 64 | Render Output Units (ROPs) | 96 |
| 19 | Compute Units (Pipelines) | — |
| No | Tensor Cores | No |
| No | Ray-tracing Cores | 60 |
| 48KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |