Quick/Comparisons
22 | Gaming | 39 |
28 | Workstation | 45 |
16 | AI/ML |
Compare with something else?
Compare GeForce GTX 1070 with another →35 |
20 | Energy Efficiency | 39 |
23 | Quick Comparison Final Score | 40 |
| GP104 | Graphics Processor | GA104 (GN20-E7) |
| 2432 | Cores | 6144 |
| 152 / 64 | TMUs / ROPs | 192 / 96 |
| 629.59 | Blender GPU | 3258.81 |
| 55 | Forza Horizon 5 | 84 |
| 77 | The Witcher 3 | 127 |
| 108 | Counter-Strike 2 | 165 |
| 70 | Far Cry 6 | 104 |
| 42 | Hogwarts Legacy | 70 |
| 53 | Call of Duty | 98 |
| 39 | Ghost of Tsushima | 66 |
| 45 | Cyberpunk 2077 | 84 |
| 80 | Tomb Raider | 129 |
| 63 | Average FPS | 103 |
| 79 | 1080p High | 125 |
| 63 | 1080p Ultra | 103 |
| 45 | 1440p Ultra | 76 |
| 24 | 4K Ultra | 44 |
| Low | Margin of Error | Low |
| 57735 | GB6 Compute Score | 128827 |
| 149.2 img/sec | Background Blur | 211 img/sec |
| 67.6 img/sec | Face Detection | 123.6 img/sec |
| 2.36 Gpixels/sec | Horizon Detection | 5.78 Gpixels/sec |
| 3.57 Gpixels/sec | Edge Detection | 8.03 Gpixels/sec |
| 4.32 Gpixels/sec | Gaussian Blur | 6.25 Gpixels/sec |
| 0.27 Gpixels/sec | Feature Matching | 1.17 Gpixels/sec |
| 209.6 Gpixels/sec | Stereo Matching | 543.2 Gpixels/sec |
| 6584.9 FPS | Particle Physics | 17774.9 FPS |
| OpenCL | API | OpenCL |
| 14658 | G3D Mark Score | 16147 |
| 876 | G2D Mark | 630 |
| 107 FPS | DirectX 11 | 145 FPS |
| 52 FPS | DirectX 12 | 71 FPS |
| 7162 Ops/s | GPU Compute | 7126 Ops/s |
| 8949 | GB6 ML Single Precision | 18354 |
| 8769 | GB6 ML Half Precision | 29767 |
| 6546 | GB6 ML Quantized | 11487 |
| 3473 | Image Classification (SP) | 6773 |
| 5149 | Image Segmentation (HP) | 19587 |
| 9722 | Image Super Resolution (Q) | 15553 |
| 9306 | Face Detection (HP) | 35885 |
| 34870 | Pose Estimation (Q) | 82446 |
| 2139 | Text Classification (SP) | 2830 |
| 2424 | Machine Translation (HP) | 4019 |
| 4566 | Object Detection (SP) | 8380 |
| 14316 | Depth Estimation (Q) | 28597 |
| 88984 | Style Transfer (SP) | 184715 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 108 GPixel/s | Pixel Fill Rate | 120-164 GPixel/s |
| 256 GTexel/s | Texture Fill Rate | 239-328 GTexel/s |
| 8.2 TFLOPS | FLOPS (FP32) | 15.3-21 TFLOPS |
| GDDR5 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 8-16 GB |
| 2002 MHz | Memory Clock | 1500-1750 MHz |
| 8000 Mbps | Effective Memory Speed | 12000-14000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 256.3 GB/s | Memory Bandwidth | 448 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x16 |
| 180 W | TGP | 80-165 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 16 nm | Fabrication Process | 8 nm |
| 314 mm² | Die Size | 392 mm² |
| 7 billion | Transistor Count | 17.4 billion |
| 22.29 MTr/mm² | Transistor Density | 44.39 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 6.1 | CUDA | 8.6 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| November 2, 2017 | Released | January 12, 2021 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Pascal | Architecture | Ampere |
| GP104 | GPU Codename | GA104 (GN20-E7) |
| -Intel Core i7 7700Kor above | Recommended CPU | -Intel Core i9 12900Hor above |
| 6671 | Steel Nomad Lite Score | 11592 |
| 6843 | Time Spy | 11991 |
| 18267 | Solar Bay | 50371 |
| 1552 | Port Royal | 7201 |
| 20115 | Fire Strike | 29067 |
| 13248 | Wild Life Extreme | 24760 |
| 78890 | Night Raid | 81949 |
| 1607 MHz | Base Clock | 780-1350 MHz (configurable) |
| 1683 MHz | Boost Clock | 1245-1710 MHz (configurable) |
| 2432 | Shading Units | 6144 |
| 152 | Texture Mapping Units (TMUs) | 192 |
| 64 | Render Output Units (ROPs) | 96 |
| 19 | Compute Units (Pipelines) | 48 |
| No | Tensor Cores | 192 |
| No | Ray-tracing Cores | 48 |
| 48KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |