Quick/Comparisons
The GeForce RTX 5070 Ti's superior gaming performance, with a score of 76, makes it the clear winner in this use case. Its large 16GB memory pool and hardware ray tracing support contribute to its dominance.
Although the GeForce GTX 1650 Ti Mobile has a slightly higher workstation score, the GeForce RTX 5070 Ti's overall score of 74 in content creation makes it the winner. Its Blackwell 2.0 architecture provides a significant advantage in this area.
The GeForce RTX 5070 Ti's score of 66 in AI/ML is significantly higher than the GeForce GTX 1650 Ti Mobile's score of 12, making it the clear winner in this use case. Its dedicated AI tensor cores and Blackwell 2.0 architecture contribute to its advantage.
12 | Gaming | 76 |
22 | Workstation | 74 |
12 | AI/ML | 66 |
65 | Energy Efficiency | 49 |
24 | Quick Comparison Final Score | 74 |
| TU117 (N18P-G62) | Graphics Processor | GB203-200-A1 |
| 1024 | Cores | 8960 |
| 64 / 32 | TMUs / ROPs | 280 / 96 |
| 442.65 | Blender GPU | 7584.67 |
| 31 | Forza Horizon 5 | 166 |
| 37 | The Witcher 3 | 213 |
| 53 | Counter-Strike 2 | 219 |
| 40 | Far Cry 6 | 159 |
| 18 | Hogwarts Legacy | 135 |
| 28 | Call of Duty | 205 |
| 15 | Ghost of Tsushima | 121 |
| 24 | Cyberpunk 2077 | 174 |
| 46 | Tomb Raider | 260 |
| 32 | Average FPS | 184 |
| 43 | 1080p High | 217 |
| 32 | 1080p Ultra | 184 |
| 23 | 1440p Ultra | 148 |
| 11 | 4K Ultra | 86 |
| Low | Margin of Error | Low |
| 47056 | GB6 Compute Score | 240508 |
| 83.5 img/sec | Background Blur | 297.9 img/sec |
| 45.7 img/sec | Face Detection | 218.6 img/sec |
| 1.77 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 2.32 Gpixels/sec | Edge Detection | 13.9 Gpixels/sec |
| 2.28 Gpixels/sec | Gaussian Blur | 14.8 Gpixels/sec |
| 0.62 Gpixels/sec | Feature Matching | 2.03 Gpixels/sec |
| 204.1 Gpixels/sec | Stereo Matching | 1290 Gpixels/sec |
| 5954.3 FPS | Particle Physics | 35438.3 FPS |
| OpenCL | API | OpenCL |
| 7540 | G3D Mark Score | 32425 |
| 372 | G2D Mark | 1329 |
| 61 FPS | DirectX 11 | 304 FPS |
| 33 FPS | DirectX 12 | 126 FPS |
| 2720 Ops/s | GPU Compute | 18089 Ops/s |
| 7029 | GB6 ML Single Precision | 36504 |
| 5688 | GB6 ML Half Precision | 64459 |
| 5358 | GB6 ML Quantized | 27312 |
| 2866 | Image Classification (SP) | 14913 |
| 3745 | Image Segmentation (HP) | 45199 |
| 6865 | Image Super Resolution (Q) | 39360 |
| 6519 | Face Detection (HP) | 84188 |
| 24706 | Pose Estimation (Q) | 161400 |
| 1793 | Text Classification (SP) | 4010 |
| 1906 | Machine Translation (HP) | 7973 |
| 3498 | Object Detection (SP) | 18934 |
| 13936 | Depth Estimation (Q) | 67761 |
| 50917 | Style Transfer (SP) | 335879 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 48 GPixel/s | Pixel Fill Rate | 235 GPixel/s |
| 95 GTexel/s | Texture Fill Rate | 687 GTexel/s |
| 3 TFLOPS | FLOPS (FP32) | 43.9 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 4 GB | Memory Size | 16 GB |
| 1500 MHz | Memory Clock | 1750 MHz |
| 12000 Mbps | Effective Memory Speed | 28000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 192 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 50 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 200 mm² | Die Size | 378 mm² |
| 4.7 billion | Transistor Count | 45.6 billion |
| 23.5 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 7.5 | CUDA | 12 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| 1.4 | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 2, 2020 | Released | January 7, 2025 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Turing | Architecture | Blackwell 2.0 |
| TU117 (N18P-G62) | GPU Codename | GB203-200-A1 |
| -Intel Core i5 10300Hor above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 3492 | Steel Nomad Lite Score | 29989 |
| 3674 | Time Spy | 27815 |
| — | Solar Bay | 136964 |
| — | Port Royal | 19613 |
| 10075 | Fire Strike | 67382 |
| 7557 | Wild Life Extreme | 57734 |
| 42903 | Night Raid | 189734 |
| 1350 MHz | Base Clock | 2295 MHz |
| 1485 MHz | Boost Clock | 2452 MHz |
| 1024 | Shading Units | 8960 |
| 64 | Texture Mapping Units (TMUs) | 280 |
| 32 | Render Output Units (ROPs) | 96 |
| 16 | Compute Units (Pipelines) | 70 |
| No | Tensor Cores | 280 |
| No | Ray-tracing Cores | 70 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 1MB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce GTX 1650 with another →