Quick/Comparisons
20 | Gaming | 5 |
29 | Workstation | 10 |
18 | AI/ML |
Compare with something else?
Compare GeForce GTX 1660 with another →4 |
44 | Energy Efficiency | 67 |
23 | Quick Comparison Final Score | 17 |
| TU116 | Graphics Processor | GP107 |
| 1536 | Cores | 640 |
| 96 / 48 | TMUs / ROPs | 32 / 16 |
| 796.71 | Blender GPU | 96.75 |
| 52 | Forza Horizon 5 | - |
| 69 | The Witcher 3 | - |
| 96 | Counter-Strike 2 | 16 |
| 64 | Far Cry 6 | 15 |
| 37 | Hogwarts Legacy | - |
| 47 | Call of Duty | 21 |
| 32 | Ghost of Tsushima | - |
| 42 | Cyberpunk 2077 | — |
| 74 | Tomb Raider | 9 |
| 57 | Average FPS | 10 |
| 74 | 1080p High | 15 |
| 57 | 1080p Ultra | 10 |
| 41 | 1440p Ultra | - |
| 21 | 4K Ultra | - |
| Low | Margin of Error | Medium |
| 72340 | GB6 Compute Score | 15572 |
| 124.8 img/sec | Background Blur | 40 img/sec |
| 69.4 img/sec | Face Detection | 18.9 img/sec |
| 2.67 Gpixels/sec | Horizon Detection | 0.59 Gpixels/sec |
| 3.48 Gpixels/sec | Edge Detection | 0.88 Gpixels/sec |
| 3.52 Gpixels/sec | Gaussian Blur | 0.97 Gpixels/sec |
| 0.92 Gpixels/sec | Feature Matching | 0.15 Gpixels/sec |
| 355.9 Gpixels/sec | Stereo Matching | 45.1 Gpixels/sec |
| 9094.4 FPS | Particle Physics | 1531.6 FPS |
| OpenCL | API | OpenCL |
| 12661 | G3D Mark Score | 2820 |
| 779 | G2D Mark | 238 |
| 103 FPS | DirectX 11 | 20 FPS |
| 51 FPS | DirectX 12 | 15 FPS |
| 5074 Ops/s | GPU Compute | 1251 Ops/s |
| 7620 | GB6 ML Quantized | 1827 |
| 4272 | Image Classification (SP) | 949 |
| 6435 | Image Segmentation (HP) | 1407 |
| 9635 | Image Super Resolution (Q) | 2693 |
| 10867 | Face Detection (HP) | 2453 |
| 41061 | Pose Estimation (Q) | 8112 |
| 1737 | Text Classification (SP) | 1170 |
| 3301 | Machine Translation (HP) | 1183 |
| 5600 | Object Detection (SP) | 768 |
| 18914 | Depth Estimation (Q) | 3878 |
| 83427 | Style Transfer (SP) | 20820 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 10788 | GB6 ML Single Precision | 2424 |
| 8753 | GB6 ML Half Precision | 2615 |
| 85 GPixel/s | Pixel Fill Rate | 15-23 GPixel/s |
| 170 GTexel/s | Texture Fill Rate | 30-47 GTexel/s |
| 5.4 TFLOPS | FLOPS (FP32) | 1.2-1.9 TFLOPS |
| GDDR6 | Memory Type | GDDR5 |
| 6 GB | Memory Size | 2 GB |
| 1500 MHz | Memory Clock | 1752 MHz |
| 12000 Mbps | Effective Memory Speed | 7000 Mbps |
| 192-bit | Bus | 64-bit |
| No | ECC | — |
| 288 GB/s | Memory Bandwidth | 56 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 3.0 x4 |
| 120 W | TGP | 15-30 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 12 nm | Fabrication Process | 14 nm |
| 284 mm² | Die Size | 132 mm² |
| 6 billion | Transistor Count | 3.3 billion |
| 21.13 MTr/mm² | Transistor Density | 25 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 1.2 |
| 7.5 | CUDA | 6.1 |
| No | Ray Tracing | No |
| No | DLSS | No |
| 1.4a | DisplayPort | 1.4 |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| February 22, 2019 | Released | February 10, 2020 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | Entry-level |
| Turing | Architecture | Pascal |
| TU116 | GPU Codename | GP107 |
| -Intel Core i5 9500or above | Recommended CPU | -Intel Core i7 1165G7or above |
| 5944 | Steel Nomad Lite Score | 967 |
| 6339 | Time Spy | 1235 |
| 20534 | Solar Bay | — |
| 1650 | Port Royal | — |
| 16653 | Fire Strike | 4234 |
| 13005 | Wild Life Extreme | 2706 |
| 76361 | Night Raid | 17008 |
| 1500 MHz | Base Clock | 747-1354 MHz (configurable) |
| 1770 MHz | Boost Clock | 936-1468 MHz (configurable) |
| 1536 | Shading Units | 640 |
| 96 | Texture Mapping Units (TMUs) | 32 |
| 48 | Render Output Units (ROPs) | 16 |
| 24 | Compute Units (Pipelines) | 5 |
| No | Tensor Cores | No |
| No | Ray-tracing Cores | No |
| 64KB per cluster | L1 Cache | 48KB per cluster |
| 1536KB shared | L2 Cache | 512KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |