Quick/Comparisons
11 | Gaming | 22 |
20 | Workstation | 17 |
13 | AI/ML |
Compare with something else?
Compare GeForce GTX 1650 with another →| — |
58 | Energy Efficiency | 66 |
15 | Quick Comparison Final Score | 28 |
| TU117 | Graphics Processor | Strix Halo |
| 896 | Cores | 1024 |
| 56 / 32 | TMUs / ROPs | 64 / 32 |
| 443.47 | Blender GPU | 376.14 |
| 32 | Forza Horizon 5 | — |
| 33 | The Witcher 3 | — |
| 54 | Counter-Strike 2 | — |
| 41 | Far Cry 6 | — |
| 21 | Hogwarts Legacy | — |
| 31 | Call of Duty | — |
| 15 | Ghost of Tsushima | — |
| 22 | Cyberpunk 2077 | — |
| 43 | Tomb Raider | — |
| 32 | Average FPS | — |
| 42 | 1080p High | — |
| 32 | 1080p Ultra | — |
| 22 | 1440p Ultra | — |
| 11 | 4K Ultra | — |
| Low | Margin of Error | — |
| 39481 | GB6 Compute Score | 35976 |
| 66.4 img/sec | Background Blur | 106.8 img/sec |
| 43.3 img/sec | Face Detection | 43.8 img/sec |
| 1.51 Gpixels/sec | Horizon Detection | 1.12 Gpixels/sec |
| 1.68 Gpixels/sec | Edge Detection | 1.17 Gpixels/sec |
| 1.87 Gpixels/sec | Gaussian Blur | 1.07 Gpixels/sec |
| 0.49 Gpixels/sec | Feature Matching | 0.5 Gpixels/sec |
| 187.9 Gpixels/sec | Stereo Matching | 163 Gpixels/sec |
| 5261.5 FPS | Particle Physics | 5820.4 FPS |
| OpenCL | API | OpenCL |
| 7871 | G3D Mark Score | 10431 |
| 553 | G2D Mark | 1094 |
| 58 FPS | DirectX 11 | 79 FPS |
| 35 FPS | DirectX 12 | 46 FPS |
| 3036 Ops/s | GPU Compute | 5066 Ops/s |
| 7569 | GB6 ML Single Precision | — |
| 5940 | GB6 ML Half Precision | — |
| 5581 | GB6 ML Quantized | — |
| 3208 | Image Classification (SP) | — |
| 4254 | Image Segmentation (HP) | — |
| 7050 | Image Super Resolution (Q) | — |
| 6849 | Face Detection (HP) | — |
| 23562 | Pose Estimation (Q) | — |
| 1755 | Text Classification (SP) | — |
| 3096 | Machine Translation (HP) | — |
| 3710 | Object Detection (SP) | — |
| 12946 | Depth Estimation (Q) | — |
| 48894 | Style Transfer (SP) | — |
| ONNX | Framework | — |
| DirectML | Backend | — |
| 53 GPixel/s | Pixel Fill Rate | 90 GPixel/s |
| 93 GTexel/s | Texture Fill Rate | 179 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 5.7 TFLOPS |
| GDDR5 | Memory Type | System Shared |
| 4 GB | Memory Size | — |
| 2001 MHz | Memory Clock | — |
| 8000 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | — |
| No | ECC | — |
| 128.1 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 75 W | TGP | 45-120 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 200 mm² | Die Size | 308 mm² |
| 4 billion | Transistor Count | — |
| 20 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 7.5 | CUDA | No |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4a | DisplayPort | 2.1a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| April 23, 2019 | Released | January 7, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| Entry-level | Segment | Mid-range |
| Turing | Architecture | RDNA 3.5 |
| TU117 | GPU Codename | Strix Halo |
| -Intel Core i5 9400or above | Recommended CPU | -AMD Ryzen AI Max Pro 380or above |
| 3419 | Steel Nomad Lite Score | — |
| 3563 | Time Spy | — |
| 12275 | Solar Bay | — |
| — | Port Royal | — |
| 9696 | Fire Strike | — |
| 7350 | Wild Life Extreme | — |
| 46189 | Night Raid | — |
| 1485 MHz | Base Clock | 1295 MHz |
| 1665 MHz | Boost Clock | 2800 MHz |
| 896 | Shading Units | 1024 |
| 56 | Texture Mapping Units (TMUs) | 64 |
| 32 | Render Output Units (ROPs) | 32 |
| 14 | Compute Units (Pipelines) | 16 |
| No | Tensor Cores | No |
| No | Ray-tracing Cores | 16 |
| 64KB per cluster | L1 Cache | 512KB per cluster |
| 1024KB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |