Quick/Comparisons
8 | Gaming | 32 |
17 | Workstation | 38 |
7 | AI/ML |
Compare with something else?
Compare GeForce GTX 1050 with another →| — |
57 | Energy Efficiency | 36 |
19 | Quick Comparison Final Score | — |
| GP107 (N17P-G1) | Graphics Processor | TU104 (N18E-G3) |
| 768 | Cores | 2944 |
| 48 / 32 | TMUs / ROPs | 184 / 64 |
| 219.05 | Blender GPU | 1573.54 |
| 18 | Forza Horizon 5 | 76 |
| 22 | The Witcher 3 | 109 |
| 28 | Counter-Strike 2 | 148 |
| 30 | Far Cry 6 | 93 |
| 13 | Hogwarts Legacy | 59 |
| 26 | Call of Duty | 82 |
| - | Ghost of Tsushima | 56 |
| 12 | Cyberpunk 2077 | 70 |
| 23 | Tomb Raider | 112 |
| 20 | Average FPS | 89 |
| 27 | 1080p High | 110 |
| 20 | 1080p Ultra | 89 |
| 14 | 1440p Ultra | 65 |
| - | 4K Ultra | 37 |
| Low | Margin of Error | Low |
| 27.8 img/sec | Face Detection | 122.4 img/sec |
| 0.84 Gpixels/sec | Horizon Detection | 4.52 Gpixels/sec |
| 1.22 Gpixels/sec | Edge Detection | 5.94 Gpixels/sec |
| 1.32 Gpixels/sec | Gaussian Blur | 6.45 Gpixels/sec |
| 0.19 Gpixels/sec | Feature Matching | 1.26 Gpixels/sec |
| 73.2 Gpixels/sec | Stereo Matching | 446.2 Gpixels/sec |
| 2037 FPS | Particle Physics | 14128.8 FPS |
| OpenCL | API | OpenCL |
| 21976 | GB6 Compute Score | 116500 |
| 57 img/sec | Background Blur | 226 img/sec |
| 5918 | G3D Mark Score | 15014 |
| 323 | G2D Mark | 804 |
| 45 FPS | DirectX 11 | 139 FPS |
| 24 FPS | DirectX 12 | 53 FPS |
| 2190 Ops/s | GPU Compute | 6463 Ops/s |
| 4032 | GB6 ML Single Precision | — |
| 3569 | GB6 ML Half Precision | — |
| 3070 | GB6 ML Quantized | — |
| 1393 | Image Classification (SP) | — |
| 2013 | Image Segmentation (HP) | — |
| 4766 | Image Super Resolution (Q) | — |
| 3370 | Face Detection (HP) | — |
| 17580 | Pose Estimation (Q) | — |
| 1319 | Text Classification (SP) | — |
| 1662 | Machine Translation (HP) | — |
| 1771 | Object Detection (SP) | — |
| 6411 | Depth Estimation (Q) | — |
| 28772 | Style Transfer (SP) | — |
| ONNX | Framework | — |
| DirectML | Backend | — |
| 52 GPixel/s | Pixel Fill Rate | 102 GPixel/s |
| 78 GTexel/s | Texture Fill Rate | 293 GTexel/s |
| 2.5 TFLOPS | FLOPS (FP32) | 9.4 TFLOPS |
| GDDR5 | Memory Type | GDDR6 |
| 4 GB | Memory Size | 8 GB |
| 1752 MHz | Memory Clock | 1500 MHz |
| 7008 Mbps | Effective Memory Speed | 12000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 112.1 GB/s | Memory Bandwidth | 384 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 3.0 x16 |
| 65 W | TGP | 150 W |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 12 nm |
| 132 mm² | Die Size | 545 mm² |
| 3.3 billion | Transistor Count | 13.6 billion |
| 25 MTr/mm² | Transistor Density | 24.95 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2.131 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 1.2 |
| 6.1 | CUDA | 7.5 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 1.4 | DisplayPort | 1.4 |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 3, 2017 | Released | January 29, 2019 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Pascal | Architecture | Turing |
| GP107 (N17P-G1) | GPU Codename | TU104 (N18E-G3) |
| -Intel Core i5 8300Hor above | Recommended CPU | -Intel Core i7 9750Hor above |
| 2303 | Steel Nomad Lite Score | 9737 |
| 2345 | Time Spy | 10053 |
| — | Solar Bay | 44509 |
| — | Port Royal | 6007 |
| 7708 | Fire Strike | 25924 |
| 4955 | Wild Life Extreme | 20417 |
| 31460 | Night Raid | 95965 |
| 1493 MHz | Base Clock | 1380 MHz |
| 1620 MHz | Boost Clock | 1590 MHz |
| 768 | Shading Units | 2944 |
| 48 | Texture Mapping Units (TMUs) | 184 |
| 32 | Render Output Units (ROPs) | 64 |
| 6 | Compute Units (Pipelines) | 46 |
| No | Tensor Cores | 368 |
| No | Ray-tracing Cores | 46 |
| 48KB per cluster | L1 Cache | 64KB per cluster |
| 1024KB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |