Quick/Comparisons
A budget Nvidia GeForce GTX 1650 Ti Mobile graphics card with limited performance overall. Suited for casual gaming and basic graphics tasks.
| Gaming | 12 /100 |
| Workstation | 22 /100 |
| AI/ML | 12 /100 |
| Energy Efficiency | 65 |
Looking for more comparisons?
Compare GeForce GTX →| Quick Comparison Final Score | 24 /100 |
| Graphics Processor | TU117 (N18P-G62) |
| Cores | 1024 |
| TMUs / ROPs | 64 / 32 |
| Blender GPU | 442.65 |
| Forza Horizon 5 | 31 |
| The Witcher 3 | 37 |
| Counter-Strike 2 | 53 |
| Far Cry 6 | 40 |
| Hogwarts Legacy | 18 |
| Call of Duty | 28 |
| Ghost of Tsushima | 15 |
| Cyberpunk 2077 | 24 |
| Tomb Raider | 46 |
| Average FPS | 32 |
| 1080p High | 43 |
| 1080p Ultra | 32 |
| 1440p Ultra | 23 |
| 4K Ultra | 11 |
| Margin of Error | Low |
| GB6 Compute Score | 47056 |
| Background Blur | 83.5 img/sec |
| Face Detection | 45.7 img/sec |
| Horizon Detection | 1.77 Gpixels/sec |
| Edge Detection | 2.32 Gpixels/sec |
| Gaussian Blur | 2.28 Gpixels/sec |
| Feature Matching | 0.62 Gpixels/sec |
| Stereo Matching | 204.1 Gpixels/sec |
| Particle Physics | 5954.3 FPS |
| API | OpenCL |
| G3D Mark Score | 7540 |
| G2D Mark | 372 |
| DirectX 11 | 61 FPS |
| DirectX 12 | 33 FPS |
| GPU Compute | 2720 Ops/s |
| GB6 ML Single Precision | 7029 |
| GB6 ML Half Precision | 5688 |
| GB6 ML Quantized | 5358 |
| Image Classification (SP) | 2866 |
| Image Segmentation (HP) | 3745 |
| Image Super Resolution (Q) | 6865 |
| Face Detection (HP) | 6519 |
| Pose Estimation (Q) | 24706 |
| Text Classification (SP) | 1793 |
| Machine Translation (HP) | 1906 |
| Object Detection (SP) | 3498 |
| Depth Estimation (Q) | 13936 |
| Style Transfer (SP) | 50917 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 48 GPixel/s |
| Texture Fill Rate | 95 GTexel/s |
| FLOPS (FP32) | 3 TFLOPS |
| Memory Type | GDDR6 |
| Memory Size | 4 GB |
| Memory Clock | 1500 MHz |
| Effective Memory Speed | 12000 Mbps |
| Bus | 128-bit |
| ECC | No |
| Memory Bandwidth | 192 GB/s |
| Interface | PCIe 3.0 x16 |
| TGP | 50 W |
| Manufacturing | TSMC |
| Fabrication Process | 12 nm |
| Die Size | 200 mm² |
| Transistor Count | 4.7 billion |
| Transistor Density | 23.5 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.2 |
| OpenGL | 4.6 |
| OpenCL | 1.2 |
| CUDA | 7.5 |
| Ray Tracing | No |
| DLSS | No |
| DisplayPort | 1.4 |
| Vendor | Nvidia |
| Build | Discrete |
| Released | April 2, 2020 |
| Case | Laptop |
| Purpose | Gaming |
| Segment | Mid-range |
| Architecture | Turing |
| GPU Codename | TU117 (N18P-G62) |
| Recommended CPU | -Intel Core i5 10300Hor above |
| Steel Nomad Lite Score | 3492 |
| Time Spy | 3674 |
| Solar Bay | — |
| Port Royal | — |
| Fire Strike | 10075 |
| Wild Life Extreme | 7557 |
| Night Raid | 42903 |
| Base Clock | 1350 MHz |
| Boost Clock | 1485 MHz |
| Shading Units | 1024 |
| Texture Mapping Units (TMUs) | 64 |
| Render Output Units (ROPs) | 32 |
| Compute Units (Pipelines) | 16 |
| Tensor Cores | No |
| Ray-tracing Cores | No |
| L1 Cache | 64KB per cluster |
| L2 Cache | 1MB shared |
| Instructions Per Cycle | 2 IPC |
GeForce RTX 5080
84/100