Quick/Comparisons
28 | Gaming | 4 |
37 | Workstation | 10 |
28 | AI/ML |
Compare with something else?
Compare Nvidia RTX 2000 with another →2 |
56 | Energy Efficiency | 71 |
35 | Quick Comparison Final Score | 17 |
| AD107 | Graphics Processor | Picasso |
| 3072 | Cores | 192 |
| 96 / 48 | TMUs / ROPs | 12 / 4 |
| 2498.74 | Blender GPU | — |
| 62 | Forza Horizon 5 | — |
| 90 | The Witcher 3 | — |
| 119 | Counter-Strike 2 | — |
| 75 | Far Cry 6 | — |
| 50 | Hogwarts Legacy | — |
| 62 | Call of Duty | — |
| 42 | Ghost of Tsushima | — |
| 52 | Cyberpunk 2077 | — |
| 88 | Tomb Raider | — |
| 71 | Average FPS | — |
| 89 | 1080p High | — |
| 71 | 1080p Ultra | — |
| 52 | 1440p Ultra | — |
| 28 | 4K Ultra | — |
| High | Margin of Error | — |
| 81913 | GB6 Compute Score | 4457 |
| 149.7 img/sec | Background Blur | 10.1 img/sec |
| 88.5 img/sec | Face Detection | 4.97 img/sec |
| 3.24 Gpixels/sec | Horizon Detection | 0.16 Gpixels/sec |
| 4.3 Gpixels/sec | Edge Detection | 0.33 Gpixels/sec |
| 4.3 Gpixels/sec | Gaussian Blur | 0.22 Gpixels/sec |
| 1.06 Gpixels/sec | Feature Matching | 0.04 Gpixels/sec |
| 278.2 Gpixels/sec | Stereo Matching | 14.1 Gpixels/sec |
| 9706.8 FPS | Particle Physics | 500.2 FPS |
| OpenCL | API | OpenCL |
| 14863 | G3D Mark Score | 892 |
| 597 | G2D Mark | 302 |
| 124 FPS | DirectX 11 | 7 FPS |
| 66 FPS | DirectX 12 | 4 FPS |
| 5612 Ops/s | GPU Compute | 442 Ops/s |
| 15637 | GB6 ML Single Precision | 1122 |
| 25753 | GB6 ML Half Precision | 1342 |
| 12373 | GB6 ML Quantized | 815 |
| 6324 | Image Classification (SP) | 476 |
| 13952 | Image Segmentation (HP) | 498 |
| 19043 | Image Super Resolution (Q) | 982 |
| 28439 | Face Detection (HP) | 1535 |
| 69947 | Pose Estimation (Q) | 2770 |
| 2887 | Text Classification (SP) | 430 |
| 3267 | Machine Translation (HP) | 706 |
| 7742 | Object Detection (SP) | 532 |
| 29911 | Depth Estimation (Q) | 1792 |
| 131880 | Style Transfer (SP) | 5517 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 60-113 GPixel/s | Pixel Fill Rate | 4-5 GPixel/s |
| 120-227 GTexel/s | Texture Fill Rate | 12-14 GTexel/s |
| 7.6-14.5 TFLOPS | FLOPS (FP32) | 0.4-0.5 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | System RAM Dependent |
| 2000 MHz | Memory Clock | System RAM Dependent |
| 16000 Mbps | Effective Memory Speed | System RAM Dependent |
| 128-bit | Bus | — |
| No | ECC | No |
| 256 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | IGP |
| 35-140 W (configurable) | TGP | 15 W |
| TSMC | Manufacturing | GlobalFoundries |
| 5 nm | Fabrication Process | 14 nm |
| 159 mm² | Die Size | 210 mm² |
| 18.9 billion | Transistor Count | 4.94 billion |
| 118.87 MTr/mm² | Transistor Density | 23.52 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.2.131 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| March 21, 2023 | Released | January 1, 2019 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Ada Lovelace | Architecture | GCN 5.0 |
| AD107 | GPU Codename | Picasso |
| -Intel Core Ultra 7 165Hor above | Recommended CPU | -AMD Ryzen 3 3200Uor above |
| 7995 | Steel Nomad Lite Score | 390 |
| 7374 | Time Spy | 412 |
| 29213 | Solar Bay | — |
| 4564 | Port Royal | — |
| 19215 | Fire Strike | 1448 |
| 14651 | Wild Life Extreme | 867 |
| 76011 | Night Raid | 6135 |
| — | Base Clock | 300 MHz |
| 1245-2360 MHz (configurable) | Boost Clock | 1000-1200 MHz (configurable) |
| 3072 | Shading Units | 192 |
| 96 | Texture Mapping Units (TMUs) | 12 |
| 48 | Render Output Units (ROPs) | 4 |
| 24 | Compute Units (Pipelines) | 3 |
| 96 | Tensor Cores | No |
| 24 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 32MB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |