Quick/Comparisons
The GeForce RTX 5070 Ti's superior gaming performance, with a score of 76, makes it the clear winner in this use case. Its 56-point lead over the GeForce GTX 1660 Ti's score of 20 is substantial.
The GeForce RTX 5070 Ti's score of 74 in content creation is 45 points higher than the GeForce GTX 1660 Ti's score of 29, making it the clear winner in this use case.
The GeForce RTX 5070 Ti's score of 66 in AI & machine learning is 48 points higher than the GeForce GTX 1660 Ti's score of 18, making it the clear winner in this use case.
20 | Gaming | 76 |
29 | Workstation | 74 |
18 | AI/ML | 66 |
44 | Energy Efficiency | 49 |
23 | Quick Comparison Final Score | 74 |
| TU116 | Graphics Processor | GB203-200-A1 |
| 1536 | Cores | 8960 |
| 96 / 48 | TMUs / ROPs | 280 / 96 |
| 796.71 | Blender GPU | 7584.67 |
| 52 | Forza Horizon 5 | 166 |
| 69 | The Witcher 3 | 213 |
| 96 | Counter-Strike 2 | 219 |
| 64 | Far Cry 6 | 159 |
| 37 | Hogwarts Legacy | 135 |
| 47 | Call of Duty | 205 |
| 32 | Ghost of Tsushima | 121 |
| 42 | Cyberpunk 2077 | 174 |
| 74 | Tomb Raider | 260 |
| 57 | Average FPS | 184 |
| 74 | 1080p High | 217 |
| 57 | 1080p Ultra | 184 |
| 41 | 1440p Ultra | 148 |
| 21 | 4K Ultra | 86 |
| Low | Margin of Error | Low |
| 72340 | GB6 Compute Score | 240508 |
| 124.8 img/sec | Background Blur | 297.9 img/sec |
| 69.4 img/sec | Face Detection | 218.6 img/sec |
| 2.67 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 3.48 Gpixels/sec | Edge Detection | 13.9 Gpixels/sec |
| 3.52 Gpixels/sec | Gaussian Blur | 14.8 Gpixels/sec |
| 0.92 Gpixels/sec | Feature Matching | 2.03 Gpixels/sec |
| 355.9 Gpixels/sec | Stereo Matching | 1290 Gpixels/sec |
| 9094.4 FPS | Particle Physics | 35438.3 FPS |
| OpenCL | API | OpenCL |
| 12661 | G3D Mark Score | 32425 |
| 779 | G2D Mark | 1329 |
| 103 FPS | DirectX 11 | 304 FPS |
| 51 FPS | DirectX 12 | 126 FPS |
| 5074 Ops/s | GPU Compute | 18089 Ops/s |
| 7620 | GB6 ML Quantized | 27312 |
| 4272 | Image Classification (SP) | 14913 |
| 6435 | Image Segmentation (HP) | 45199 |
| 9635 | Image Super Resolution (Q) | 39360 |
| 10867 | Face Detection (HP) | 84188 |
| 41061 | Pose Estimation (Q) | 161400 |
| 1737 | Text Classification (SP) | 4010 |
| 3301 | Machine Translation (HP) | 7973 |
| 5600 | Object Detection (SP) | 18934 |
| 18914 | Depth Estimation (Q) | 67761 |
| 83427 | Style Transfer (SP) | 335879 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 10788 | GB6 ML Single Precision | 36504 |
| 8753 | GB6 ML Half Precision | 64459 |
| 85 GPixel/s | Pixel Fill Rate | 235 GPixel/s |
| 170 GTexel/s | Texture Fill Rate | 687 GTexel/s |
| 5.4 TFLOPS | FLOPS (FP32) | 43.9 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 6 GB | Memory Size | 16 GB |
| 1500 MHz | Memory Clock | 1750 MHz |
| 12000 Mbps | Effective Memory Speed | 28000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | No |
| 288 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 120 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 284 mm² | Die Size | 378 mm² |
| 6 billion | Transistor Count | 45.6 billion |
| 21.13 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 7.5 | CUDA | 12 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| February 22, 2019 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | Mid-range |
| Turing | Architecture | Blackwell 2.0 |
| TU116 | GPU Codename | GB203-200-A1 |
| -Intel Core i5 9500or above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 5944 | Steel Nomad Lite Score | 29989 |
| 6339 | Time Spy | 27815 |
| 20534 | Solar Bay | 136964 |
| 1650 | Port Royal | 19613 |
| 16653 | Fire Strike | 67382 |
| 13005 | Wild Life Extreme | 57734 |
| 76361 | Night Raid | 189734 |
| 1500 MHz | Base Clock | 2295 MHz |
| 1770 MHz | Boost Clock | 2452 MHz |
| 1536 | Shading Units | 8960 |
| 96 | Texture Mapping Units (TMUs) | 280 |
| 48 | Render Output Units (ROPs) | 96 |
| 24 | Compute Units (Pipelines) | 70 |
| No | Tensor Cores | 280 |
| No | Ray-tracing Cores | 70 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 1536KB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce GTX 1660 with another →