Quick/Comparisons
40 | Gaming | 5 |
40 | Workstation | 11 |
31 | AI/ML |
Compare with something else?
Compare Nvidia RTX 2000 with another →4 |
74 | Energy Efficiency | 89 |
39 | Quick Comparison Final Score | 20 |
| AD107 | Graphics Processor | Mendocino |
| 2816 | Cores | 128 |
| 88 / 48 | TMUs / ROPs | 8 / 4 |
| 2690.32 | Blender GPU | 47.24 |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 89677 | GB6 Compute Score | 5099 |
| 170.5 img/sec | Background Blur | 12 img/sec |
| 102.8 img/sec | Face Detection | 6.42 img/sec |
| 3.25 Gpixels/sec | Horizon Detection | 0.16 Gpixels/sec |
| 4.12 Gpixels/sec | Edge Detection | 0.23 Gpixels/sec |
| 4.06 Gpixels/sec | Gaussian Blur | 0.16 Gpixels/sec |
| 1.13 Gpixels/sec | Feature Matching | 0.07 Gpixels/sec |
| 353.4 Gpixels/sec | Stereo Matching | 18.2 Gpixels/sec |
| 12273.1 FPS | Particle Physics | 828.6 FPS |
| OpenCL | API | OpenCL |
| 17146 | G3D Mark Score | 1810 |
| 1094 | G2D Mark | 536 |
| 140 FPS | DirectX 11 | 17 FPS |
| 72 FPS | DirectX 12 | 7 FPS |
| 7990 Ops/s | GPU Compute | 771 Ops/s |
| 15501 | GB6 ML Single Precision | 1917 |
| 27554 | GB6 ML Half Precision | 2053 |
| 12117 | GB6 ML Quantized | 1571 |
| 6382 | Image Classification (SP) | 660 |
| 16489 | Image Segmentation (HP) | 627 |
| 17694 | Image Super Resolution (Q) | 2053 |
| 32453 | Face Detection (HP) | 2153 |
| 56937 | Pose Estimation (Q) | 5787 |
| 3097 | Text Classification (SP) | 713 |
| 4324 | Machine Translation (HP) | 1114 |
| 7656 | Object Detection (SP) | 709 |
| 29700 | Depth Estimation (Q) | 3233 |
| 116441 | Style Transfer (SP) | 11091 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 102 GPixel/s | Pixel Fill Rate | 8-9 GPixel/s |
| 187 GTexel/s | Texture Fill Rate | 15-18 GTexel/s |
| 12 TFLOPS | FLOPS (FP32) | 0.5-0.6 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 16 GB | Memory Size | — |
| 2000 MHz | Memory Clock | — |
| 16000 Mbps | Effective Memory Speed | — |
| 128-bit | Bus | — |
| No | ECC | No |
| 256 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x8 |
| 70 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 6 nm |
| 159 mm² | Die Size | 122 mm² |
| 18 billion | Transistor Count | 3.4 billion |
| 113.21 MTr/mm² | Transistor Density | 27.87 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| February 12, 2022 | Released | October 1, 2022 |
| Desktop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Ada Lovelace | Architecture | RDNA 2.0 |
| AD107 | GPU Codename | Mendocino |
| -Intel Core i7 14700Kor above | Recommended CPU | -AMD Ryzen 5 7520Uor above |
| — | Steel Nomad Lite Score | 447 |
| — | Time Spy | 519 |
| — | Solar Bay | 2078 |
| — | Port Royal | 309 |
| — | Fire Strike | 1760 |
| — | Wild Life Extreme | 994 |
| — | Night Raid | 7447 |
| 1620 MHz | Base Clock | 400 MHz |
| 2130 MHz | Boost Clock | 1900-2200 MHz (configurable) |
| 2816 | Shading Units | 128 |
| 88 | Texture Mapping Units (TMUs) | 8 |
| 48 | Render Output Units (ROPs) | 4 |
| 22 | Compute Units (Pipelines) | 2 |
| 88 | Tensor Cores | — |
| 22 | Ray-tracing Cores | 2 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 12MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |