Quick/Comparisons
11 | Gaming | 6 |
21 | Workstation | 14 |
12 | AI/ML |
Compare with something else?
Compare GeForce GTX 1650 with another →7 |
65 | Energy Efficiency | 71 |
23 | Quick Comparison Final Score | 19 |
| TU117 | Graphics Processor | TU117 |
| 1024 | Cores | 896 |
| 64 / 32 | TMUs / ROPs | 56 / 32 |
| 378.08 | Blender GPU | 201.01 |
| 29 | Forza Horizon 5 | 10 |
| 33 | The Witcher 3 | 12 |
| 48 | Counter-Strike 2 | 22 |
| 39 | Far Cry 6 | 21 |
| 17 | Hogwarts Legacy | 10 |
| 27 | Call of Duty | 23 |
| 15 | Ghost of Tsushima | - |
| 20 | Cyberpunk 2077 | - |
| 42 | Tomb Raider | 17 |
| 30 | Average FPS | 14 |
| 39 | 1080p High | 20 |
| 30 | 1080p Ultra | 14 |
| 20 | 1440p Ultra | 10 |
| 11 | 4K Ultra | - |
| Low | Margin of Error | Medium |
| 40588 | GB6 Compute Score | 34221 |
| 74.4 img/sec | Background Blur | 65.7 img/sec |
| 42 img/sec | Face Detection | 33.3 img/sec |
| 1.47 Gpixels/sec | Horizon Detection | 1.01 Gpixels/sec |
| 1.93 Gpixels/sec | Edge Detection | 1.39 Gpixels/sec |
| 1.81 Gpixels/sec | Gaussian Blur | 1.61 Gpixels/sec |
| 0.52 Gpixels/sec | Feature Matching | 0.48 Gpixels/sec |
| 187 Gpixels/sec | Stereo Matching | 176 Gpixels/sec |
| 5347.1 FPS | Particle Physics | 5012.4 FPS |
| OpenCL | API | OpenCL |
| 6968 | G3D Mark Score | 3718 |
| 384 | G2D Mark | 305 |
| 50 FPS | DirectX 11 | 26 FPS |
| 27 FPS | DirectX 12 | 23 FPS |
| 2750 Ops/s | GPU Compute | 1867 Ops/s |
| 7029 | GB6 ML Single Precision | 4394 |
| 5688 | GB6 ML Half Precision | 4387 |
| 5358 | GB6 ML Quantized | 3246 |
| 2866 | Image Classification (SP) | 1911 |
| 3745 | Image Segmentation (HP) | 2536 |
| 6865 | Image Super Resolution (Q) | 4111 |
| 6519 | Face Detection (HP) | 5175 |
| 24706 | Pose Estimation (Q) | 13374 |
| 1793 | Text Classification (SP) | 1514 |
| 1906 | Machine Translation (HP) | 1481 |
| 3498 | Object Detection (SP) | 2070 |
| 13936 | Depth Estimation (Q) | 7813 |
| 50917 | Style Transfer (SP) | 36156 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 50 GPixel/s | Pixel Fill Rate | 30-50 GPixel/s |
| 100 GTexel/s | Texture Fill Rate | 52-88 GTexel/s |
| 3.2 TFLOPS | FLOPS (FP32) | 1.7-2.8 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 4 GB | Memory Size | 2 GB |
| 1500 MHz | Memory Clock | 1250 MHz |
| 12000 Mbps | Effective Memory Speed | 10000 Mbps |
| 128-bit | Bus | 64-bit |
| No | ECC | — |
| 192 GB/s | Memory Bandwidth | 80 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x4 |
| 50 W | TGP | 10-30 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 12 nm |
| 200 mm² | Die Size | 200 mm² |
| 4.7 billion | Transistor Count | 4.7 billion |
| 23.5 MTr/mm² | Transistor Density | 23.5 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 1.2 |
| 7.5 | CUDA | 7.5 |
| No | Ray Tracing | No |
| No | DLSS | No |
| 1.4 | DisplayPort | 1.4 |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 15, 2020 | Released | August 25, 2020 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Turing | Architecture | Turing |
| TU117 | GPU Codename | TU117 |
| -Intel Core i5 10300Hor above | Recommended CPU | -Intel Core i5 11300Hor above |
| 3260 | Steel Nomad Lite Score | 1174 |
| 3442 | Time Spy | 2118 |
| — | Solar Bay | — |
| 6905 | Port Royal | — |
| 9312 | Fire Strike | 5267 |
| 6928 | Wild Life Extreme | 4259 |
| 40578 | Night Raid | 26243 |
| 64KB per cluster | L1 Cache | 64KB per cluster |
| 1024KB shared | L2 Cache | 512KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
| 1380 MHz | Base Clock | 720-1395 MHz (configurable) |
| 1560 MHz | Boost Clock | 930-1575 MHz (configurable) |
| 1024 | Shading Units | 896 |
| 64 | Texture Mapping Units (TMUs) | 56 |
| 32 | Render Output Units (ROPs) | 32 |
| 16 | Compute Units (Pipelines) | 14 |
| No | Tensor Cores | No |
| No | Ray-tracing Cores | No |