Quick/Comparisons
The GeForce RTX 5060 Ti (16GB) outperforms the GeForce GTX 1050 by a significant margin, thanks to its 43-point difference in gaming scores.
Both GPUs have identical workstation scores, indicating a tie in content creation performance.
The GeForce RTX 5060 Ti (16GB) leads the GeForce GTX 1050 by 40 points in AI/ML scores, thanks to its dedicated hardware capabilities.
7 | Gaming | 50 |
16 | Workstation | 50 |
6 | AI/ML |
Compare with something else?
Compare GeForce GTX 1050 with another →46 |
54 | Energy Efficiency | 48 |
11 | Quick Comparison Final Score | 49 |
| GP107 | Graphics Processor | GB206-300 |
| 640 | Cores | 4608 |
| 40 / 32 | TMUs / ROPs | 144 / 48 |
| 170.66 | Blender GPU | 4318.61 |
| 11 | Forza Horizon 5 | 108 |
| 15 | The Witcher 3 | 152 |
| 21 | Counter-Strike 2 | 200 |
| 24 | Far Cry 6 | 130 |
| 10 | Hogwarts Legacy | 91 |
| 25 | Call of Duty | 130 |
| - | Ghost of Tsushima | 83 |
| - | Cyberpunk 2077 | 106 |
| 17 | Tomb Raider | 179 |
| 15 | Average FPS | 131 |
| 22 | 1080p High | 156 |
| 15 | 1080p Ultra | 131 |
| 11 | 1440p Ultra | 99 |
| - | 4K Ultra | 58 |
| Low | Margin of Error | Low |
| 20580 | GB6 Compute Score | 148626 |
| 52.5 img/sec | Background Blur | 243.1 img/sec |
| 24.9 img/sec | Face Detection | 149.5 img/sec |
| 0.79 Gpixels/sec | Horizon Detection | 5.35 Gpixels/sec |
| 1.16 Gpixels/sec | Edge Detection | 6.88 Gpixels/sec |
| 1.25 Gpixels/sec | Gaussian Blur | 7.76 Gpixels/sec |
| 0.2 Gpixels/sec | Feature Matching | 1.57 Gpixels/sec |
| 65.5 Gpixels/sec | Stereo Matching | 740.2 Gpixels/sec |
| 1832.4 FPS | Particle Physics | 22183.7 FPS |
| OpenCL | API | OpenCL |
| 5046 | G3D Mark Score | 22659 |
| 457 | G2D Mark | 1212 |
| 38 FPS | DirectX 11 | 219 FPS |
| 21 FPS | DirectX 12 | 89 FPS |
| 2105 Ops/s | GPU Compute | 11327 Ops/s |
| 3704 | GB6 ML Single Precision | 24763 |
| 3258 | GB6 ML Half Precision | 47486 |
| 2694 | GB6 ML Quantized | 18826 |
| 1249 | Image Classification (SP) | 10281 |
| 1833 | Image Segmentation (HP) | 29909 |
| 3934 | Image Super Resolution (Q) | 26549 |
| 3004 | Face Detection (HP) | 59010 |
| 14474 | Pose Estimation (Q) | 117200 |
| 1249 | Text Classification (SP) | 3993 |
| 1857 | Machine Translation (HP) | 6647 |
| 1624 | Object Detection (SP) | 12742 |
| 5567 | Depth Estimation (Q) | 44856 |
| 24188 | Style Transfer (SP) | 175892 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 47 GPixel/s | Pixel Fill Rate | 123 GPixel/s |
| 58 GTexel/s | Texture Fill Rate | 370 GTexel/s |
| 1.9 TFLOPS | FLOPS (FP32) | 23.7 TFLOPS |
| GDDR5 | Memory Type | GDDR7 |
| 2 GB | Memory Size | 16 GB |
| 1752 MHz | Memory Clock | 1750 MHz |
| 7000 Mbps | Effective Memory Speed | 28000 Mbps |
| 128-bit | Bus | 128-bit |
| No | ECC | No |
| 112.1 GB/s | Memory Bandwidth | 448 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x8 |
| 75 W | TGP | 180 W |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 5 nm |
| 132 mm² | Die Size | 181 mm² |
| 3 billion | Transistor Count | 21.9 billion |
| 22.73 MTr/mm² | Transistor Density | 120.99 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 6.1 | CUDA | 12 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| October 25, 2016 | Released | April 15, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | Mid-range |
| Pascal | Architecture | Blackwell 2.0 |
| GP107 | GPU Codename | GB206-300 |
| -Intel Core i5 7400or above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 1830 | Steel Nomad Lite Score | 16221 |
| 1738 | Time Spy | 16029 |
| — | Solar Bay | 75759 |
| — | Port Royal | 10220 |
| 6771 | Fire Strike | 42444 |
| 3874 | Wild Life Extreme | 30222 |
| 27072 | Night Raid | 152055 |
| 1354 MHz | Base Clock | 2407 MHz |
| 1455 MHz | Boost Clock | 2572 MHz |
| 640 | Shading Units | 4608 |
| 40 | Texture Mapping Units (TMUs) | 144 |
| 32 | Render Output Units (ROPs) | 48 |
| 5 | Compute Units (Pipelines) | 36 |
| No | Tensor Cores | 144 |
| No | Ray-tracing Cores | 36 |
| 48KB per cluster | L1 Cache | 128KB per cluster |
| 1024KB shared | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |