Quick/Comparisons
A entry-level Nvidia RTX 2000 Laptop (Ada) graphics card with modest workstation performance (37/100). Suited for casual gaming and basic graphics tasks.
| Gaming | 28 /100 |
| Workstation | 37 /100 |
| AI/ML | 28 /100 |
| Energy Efficiency | 56 |
Looking for more comparisons?
Compare Nvidia RTX →| Quick Comparison Final Score | 35 /100 |
| Graphics Processor | AD107 |
| Cores | 3072 |
| TMUs / ROPs | 96 / 48 |
| Blender GPU | 2498.74 |
| Forza Horizon 5 | 62 |
| The Witcher 3 | 90 |
| Counter-Strike 2 | 119 |
| Far Cry 6 | 75 |
| Hogwarts Legacy | 50 |
| Call of Duty | 62 |
| Ghost of Tsushima | 42 |
| Cyberpunk 2077 | 52 |
| Tomb Raider | 88 |
| Average FPS | 71 |
| 1080p High | 89 |
| 1080p Ultra | 71 |
| 1440p Ultra | 52 |
| 4K Ultra | 28 |
| Margin of Error | High |
| GB6 Compute Score | 81913 |
| Background Blur | 149.7 img/sec |
| Face Detection | 88.5 img/sec |
| Horizon Detection | 3.24 Gpixels/sec |
| Edge Detection | 4.3 Gpixels/sec |
| Gaussian Blur | 4.3 Gpixels/sec |
| Feature Matching | 1.06 Gpixels/sec |
| Stereo Matching | 278.2 Gpixels/sec |
| Particle Physics | 9706.8 FPS |
| API | OpenCL |
| G3D Mark Score | 14863 |
| G2D Mark | 597 |
| DirectX 11 | 124 FPS |
| DirectX 12 | 66 FPS |
| GPU Compute | 5612 Ops/s |
| GB6 ML Single Precision | 15637 |
| GB6 ML Half Precision | 25753 |
| GB6 ML Quantized | 12373 |
| Image Classification (SP) | 6324 |
| Image Segmentation (HP) | 13952 |
| Image Super Resolution (Q) | 19043 |
| Face Detection (HP) | 28439 |
| Pose Estimation (Q) | 69947 |
| Text Classification (SP) | 2887 |
| Machine Translation (HP) | 3267 |
| Object Detection (SP) | 7742 |
| Depth Estimation (Q) | 29911 |
| Style Transfer (SP) | 131880 |
| Framework | ONNX |
| Backend | DirectML |
| Pixel Fill Rate | 60-113 GPixel/s |
| Texture Fill Rate | 120-227 GTexel/s |
| FLOPS (FP32) | 7.6-14.5 TFLOPS |
| Memory Type | GDDR6 |
| Memory Size | 8 GB |
| Memory Clock | 2000 MHz |
| Effective Memory Speed | 16000 Mbps |
| Bus | 128-bit |
| ECC | No |
| Memory Bandwidth | 256 GB/s |
| Interface | PCIe 4.0 x16 |
| TGP | 35-140 W (configurable) |
| Manufacturing | TSMC |
| Fabrication Process | 5 nm |
| Die Size | 159 mm² |
| Transistor Count | 18.9 billion |
| Transistor Density | 118.87 MTr/mm² |
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3 |
| CUDA | 8.9 |
| Ray Tracing | Yes |
| DLSS | DLSS 3 |
| DisplayPort | 1.4a |
| Vendor | Nvidia |
| Build | Discrete |
| Released | March 21, 2023 |
| Case | Laptop |
| Purpose | Professional |
| Segment | Mid-range |
| Architecture | Ada Lovelace |
| GPU Codename | AD107 |
| Recommended CPU | -Intel Core Ultra 7 165Hor above |
| Steel Nomad Lite Score | 7995 |
| Time Spy | 7374 |
| Solar Bay | 29213 |
| Port Royal | 4564 |
| Fire Strike | 19215 |
| Wild Life Extreme | 14651 |
| Night Raid | 76011 |
| Base Clock | — |
| Boost Clock | 1245-2360 MHz (configurable) |
| Shading Units | 3072 |
| Texture Mapping Units (TMUs) | 96 |
| Render Output Units (ROPs) | 48 |
| Compute Units (Pipelines) | 24 |
| Tensor Cores | 96 |
| Ray-tracing Cores | 24 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 32MB shared |
| Instructions Per Cycle | 2 IPC |
GeForce RTX 5080
84/100