Quick/Comparisons
17 | Gaming | 56 |
29 | Workstation | 67 |
18 | AI/ML |
Compare with something else?
Compare Nvidia RTX A2000 with another →53 |
59 | Energy Efficiency | 49 |
27 | Quick Comparison Final Score | 57 |
| GA106 | Graphics Processor | GB203-300-A1 |
| 2560 | Cores | 7680 |
| 80 / 48 | TMUs / ROPs | 240 / 96 |
| 1262.73 | Blender GPU | 5699.95 |
| 44 | Forza Horizon 5 | 114 |
| 47 | The Witcher 3 | 157 |
| 74 | Counter-Strike 2 | 204 |
| 50 | Far Cry 6 | 132 |
| 26 | Hogwarts Legacy | 96 |
| 36 | Call of Duty | 143 |
| 23 | Ghost of Tsushima | 87 |
| 33 | Cyberpunk 2077 | 118 |
| 56 | Tomb Raider | 197 |
| 43 | Average FPS | 139 |
| 55 | 1080p High | 166 |
| 43 | 1080p Ultra | 139 |
| 30 | 1440p Ultra | 106 |
| 14 | 4K Ultra | 63 |
| Low | Margin of Error | High |
| 57201 | GB6 Compute Score | 197909 |
| 92.8 img/sec | Background Blur | 267.1 img/sec |
| 54.2 img/sec | Face Detection | 165.5 img/sec |
| 2.47 Gpixels/sec | Horizon Detection | 8.72 Gpixels/sec |
| 3.32 Gpixels/sec | Edge Detection | 12.3 Gpixels/sec |
| 2.63 Gpixels/sec | Gaussian Blur | 12.6 Gpixels/sec |
| 0.7 Gpixels/sec | Feature Matching | 1.83 Gpixels/sec |
| 236.9 Gpixels/sec | Stereo Matching | 942.6 Gpixels/sec |
| 7148.8 FPS | Particle Physics | 25637.1 FPS |
| OpenCL | API | OpenCL |
| 9487 | G3D Mark Score | 23401 |
| 505 | G2D Mark | 874 |
| 65 FPS | DirectX 11 | 232 FPS |
| 47 FPS | DirectX 12 | 109 FPS |
| 4252 Ops/s | GPU Compute | 8154 Ops/s |
| 9891 | GB6 ML Single Precision | 27844 |
| 18270 | GB6 ML Half Precision | 48544 |
| 6987 | GB6 ML Quantized | 21478 |
| 4240 | Image Classification (SP) | 11723 |
| 9190 | Image Segmentation (HP) | 32142 |
| 9374 | Image Super Resolution (Q) | 30735 |
| 18335 | Face Detection (HP) | 58722 |
| 36989 | Pose Estimation (Q) | 129551 |
| 2035 | Text Classification (SP) | 3539 |
| 2687 | Machine Translation (HP) | 6242 |
| 5174 | Object Detection (SP) | 14495 |
| 16537 | Depth Estimation (Q) | 50690 |
| 77854 | Style Transfer (SP) | 231154 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 50-81 GPixel/s | Pixel Fill Rate | 163-180 GPixel/s |
| 83-136 GTexel/s | Texture Fill Rate | 408-450 GTexel/s |
| 5.3-8.7 TFLOPS | FLOPS (FP32) | 26.1-28.8 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 4.0 x16 | Interface | PCIe 5.0 x16 |
| 60-95 W (configurable) | TGP | 80-175 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 276 mm² | Die Size | 378 mm² |
| 12 billion | Transistor Count | 45.6 billion |
| 43.48 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 12, 2021 | Released | March 18, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA106 | GPU Codename | GB203-300-A1 |
| -Intel Core i7 12800Hor above | Recommended CPU | -Intel Core Ultra 9 275HXor above |
| 4397 | Steel Nomad Lite Score | 22035 |
| 4723 | Time Spy | 13961 |
| 19912 | Solar Bay | — |
| 2895 | Port Royal | 12094 |
| 11357 | Fire Strike | 38402 |
| 8429 | Wild Life Extreme | — |
| 49889 | Night Raid | — |
| 735-1463 MHz (configurable) | Base Clock | 975-1702 MHz (configurable) |
| 1035-1695 MHz (configurable) | Boost Clock | 1702-1875 MHz (configurable) |
| 2560 | Shading Units | 7680 |
| 80 | Texture Mapping Units (TMUs) | 240 |
| 48 | Render Output Units (ROPs) | 96 |
| 20 | Compute Units (Pipelines) | 60 |
| 80 | Tensor Cores | 240 |
| 20 | Ray-tracing Cores | 60 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |