Quick/Comparisons
38 | Gaming | 14 |
42 | Workstation | 21 |
31 | AI/ML |
Compare with something else?
Compare GeForce RTX 3060 with another →11 |
35 | Energy Efficiency | 68 |
38 | Quick Comparison Final Score | 25 |
| GA104 | Graphics Processor | TU117 |
| 4864 | Cores | 896 |
| 152 / 80 | TMUs / ROPs | 56 / 32 |
| 2992.04 | Blender GPU | 417.51 |
| 87 | Forza Horizon 5 | — |
| 124 | The Witcher 3 | — |
| 167 | Counter-Strike 2 | — |
| 106 | Far Cry 6 | — |
| 71 | Hogwarts Legacy | — |
| 100 | Call of Duty | — |
| 68 | Ghost of Tsushima | — |
| 82 | Cyberpunk 2077 | — |
| 128 | Tomb Raider | — |
| 104 | Average FPS | — |
| 127 | 1080p High | — |
| 104 | 1080p Ultra | — |
| 77 | 1440p Ultra | — |
| 43 | 4K Ultra | — |
| Low | Margin of Error | — |
| 115518 | GB6 Compute Score | 33110 |
| 185.1 img/sec | Background Blur | 61.6 img/sec |
| 108.4 img/sec | Face Detection | 31.3 img/sec |
| 5.35 Gpixels/sec | Horizon Detection | 1.17 Gpixels/sec |
| 7.17 Gpixels/sec | Edge Detection | 1.48 Gpixels/sec |
| 5.54 Gpixels/sec | Gaussian Blur | 1.8 Gpixels/sec |
| 1.15 Gpixels/sec | Feature Matching | 0.43 Gpixels/sec |
| 478 Gpixels/sec | Stereo Matching | 149.1 Gpixels/sec |
| 15183 FPS | Particle Physics | 4185.6 FPS |
| OpenCL | API | OpenCL |
| 20272 | G3D Mark Score | 7038 |
| 990 | G2D Mark | 482 |
| 164 FPS | DirectX 11 | 51 FPS |
| 78 FPS | DirectX 12 | 32 FPS |
| 9905 Ops/s | GPU Compute | 2678 Ops/s |
| 17811 | GB6 ML Single Precision | 6235 |
| 29969 | GB6 ML Half Precision | 4946 |
| 11367 | GB6 ML Quantized | 4599 |
| 7384 | Image Classification (SP) | 2490 |
| 19320 | Image Segmentation (HP) | 3507 |
| 16108 | Image Super Resolution (Q) | 6427 |
| 34615 | Face Detection (HP) | 5241 |
| 74811 | Pose Estimation (Q) | 21102 |
| 2638 | Text Classification (SP) | 1520 |
| 4136 | Machine Translation (HP) | 2350 |
| 8718 | Object Detection (SP) | 2982 |
| 25946 | Depth Estimation (Q) | 10665 |
| 153275 | Style Transfer (SP) | 43183 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 133 GPixel/s | Pixel Fill Rate | 45 GPixel/s |
| 253 GTexel/s | Texture Fill Rate | 78 GTexel/s |
| 16.2 TFLOPS | FLOPS (FP32) | 2.5 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 4 GB |
| 1750 MHz | Memory Clock | 1250 MHz |
| 14000 Mbps | Effective Memory Speed | 10000 Mbps |
| 256-bit | Bus | 128-bit |
| No | ECC | — |
| 448 GB/s | Memory Bandwidth | 160 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 3.0 x16 |
| 200 W | TGP | 40 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 12 nm |
| 392 mm² | Die Size | 200 mm² |
| 17 billion | Transistor Count | 4.7 billion |
| 43.37 MTr/mm² | Transistor Density | 23.5 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 7.5 |
| Yes | Ray Tracing | No |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 1.4 |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| December 2, 2020 | Released | April 12, 2021 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | Entry-level |
| Ampere | Architecture | Turing |
| GA104 | GPU Codename | TU117 |
| -Intel Core i5 12600Kor above | Recommended CPU | -Intel Core i7 11800Hor above |
| 11978 | Steel Nomad Lite Score | — |
| 11707 | Time Spy | — |
| 54374 | Solar Bay | — |
| 6971 | Port Royal | — |
| 29568 | Fire Strike | — |
| 24415 | Wild Life Extreme | — |
| 109854 | Night Raid | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |
| 1410 MHz | Base Clock | 930 MHz |
| 1665 MHz | Boost Clock | 1395 MHz |
| 4864 | Shading Units | 896 |
| 152 | Texture Mapping Units (TMUs) | 56 |
| 80 | Render Output Units (ROPs) | 32 |
| 38 | Compute Units (Pipelines) | 14 |
| 152 | Tensor Cores | — |
| 38 | Ray-tracing Cores | — |
| 128KB per cluster | L1 Cache | 64KB per cluster |
| 4MB shared | L2 Cache | 1MB shared |