Quick/Comparisons
31 | Gaming | 12 |
37 | Workstation | 16 |
29 | AI/ML |
Compare with something else?
Compare GeForce RTX 3060 with another →18 |
37 | Energy Efficiency | 89 |
33 | Quick Comparison Final Score | 26 |
| GA106 | Graphics Processor | Arrow Lake iGPU |
| 3584 | Cores | 1024 |
| 112 / 48 | TMUs / ROPs | 64 / 32 |
| 2303.56 | Blender GPU | 765.53 |
| 71 | Forza Horizon 5 | 29 |
| 100 | The Witcher 3 | 33 |
| 133 | Counter-Strike 2 | 33 |
| 83 | Far Cry 6 | 35 |
| 56 | Hogwarts Legacy | 14 |
| 73 | Call of Duty | 27 |
| 49 | Ghost of Tsushima | 17 |
| 62 | Cyberpunk 2077 | 20 |
| 97 | Tomb Raider | 35 |
| 80 | Average FPS | 27 |
| 100 | 1080p High | 35 |
| 80 | 1080p Ultra | 27 |
| 59 | 1440p Ultra | 19 |
| 32 | 4K Ultra | 10 |
| Low | Margin of Error | Low |
| 91603 | GB6 Compute Score | 42502 |
| 149.6 img/sec | Background Blur | 90 img/sec |
| 91 img/sec | Face Detection | 39.5 img/sec |
| 4.07 Gpixels/sec | Horizon Detection | 1.21 Gpixels/sec |
| 5.58 Gpixels/sec | Edge Detection | 1.52 Gpixels/sec |
| 3.92 Gpixels/sec | Gaussian Blur | 2.41 Gpixels/sec |
| 1.01 Gpixels/sec | Feature Matching | 0.51 Gpixels/sec |
| 372.9 Gpixels/sec | Stereo Matching | 161.8 Gpixels/sec |
| 12226.3 FPS | Particle Physics | 9155.9 FPS |
| OpenCL | API | OpenCL |
| 16744 | G3D Mark Score | 6620 |
| 966 | G2D Mark | 835 |
| 128 FPS | DirectX 11 | 47 FPS |
| 69 FPS | DirectX 12 | 29 FPS |
| 8266 Ops/s | GPU Compute | 2992 Ops/s |
| 15123 | GB6 ML Single Precision | 8764 |
| 25942 | GB6 ML Half Precision | 12046 |
| 10356 | GB6 ML Quantized | 5815 |
| 6645 | Image Classification (SP) | 5224 |
| 15338 | Image Segmentation (HP) | 10501 |
| 14283 | Image Super Resolution (Q) | 6436 |
| 28862 | Face Detection (HP) | 15277 |
| 61313 | Pose Estimation (Q) | 19008 |
| 2463 | Text Classification (SP) | 1566 |
| 3793 | Machine Translation (HP) | 2969 |
| 7712 | Object Detection (SP) | 6172 |
| 25461 | Depth Estimation (Q) | 14526 |
| 123233 | Style Transfer (SP) | 62049 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 85 GPixel/s | Pixel Fill Rate | 72-75 GPixel/s |
| 199 GTexel/s | Texture Fill Rate | 144-150 GTexel/s |
| 12.7 TFLOPS | FLOPS (FP32) | 4.6-4.8 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 12 GB | Memory Size | — |
| 1875 MHz | Memory Clock | — |
| 15000 Mbps | Effective Memory Speed | — |
| 192-bit | Bus | — |
| No | ECC | — |
| 360 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 170 W | TGP | 35 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 276 mm² | Die Size | — |
| 12 billion | Transistor Count | — |
| 43.48 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| January 12, 2021 | Released | January 6, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Ampere | Architecture | Xe+ |
| GA106 | GPU Codename | Arrow Lake iGPU |
| -Intel Core i5 12600Kor above | Recommended CPU | -Intel Core Ultra 5 235Hor above |
| 9002 | Steel Nomad Lite Score | 3255 |
| 8754 | Time Spy | 3793 |
| 41139 | Solar Bay | 14650 |
| 5145 | Port Royal | 1990 |
| 22306 | Fire Strike | 8598 |
| 17726 | Wild Life Extreme | 6648 |
| 97592 | Night Raid | 38856 |
| 1320 MHz | Base Clock | 300 MHz |
| 1777 MHz | Boost Clock | 2250-2350 MHz (configurable) |
| 3584 | Shading Units | 1024 |
| 112 | Texture Mapping Units (TMUs) | 64 |
| 48 | Render Output Units (ROPs) | 32 |
| 28 | Compute Units (Pipelines) | 8 |
| 112 | Tensor Cores | 128 |
| 28 | Ray-tracing Cores | 8 |
| 128KB per cluster | L1 Cache | — |
| 3MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |