Quick/Comparisons
42 | Gaming | 5 |
48 | Workstation | 11 |
37 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →4 |
37 | Energy Efficiency | 89 |
42 | Quick Comparison Final Score | 20 |
| GA103 (GN20-E8) | Graphics Processor | Mendocino |
| 7424 | Cores | 128 |
| 232 / 96 | TMUs / ROPs | 8 / 4 |
| 3502.46 | Blender GPU | 47.24 |
| 92 | Forza Horizon 5 | — |
| 136 | The Witcher 3 | — |
| 181 | Counter-Strike 2 | — |
| 111 | Far Cry 6 | — |
| 79 | Hogwarts Legacy | — |
| 106 | Call of Duty | — |
| 72 | Ghost of Tsushima | — |
| 86 | Cyberpunk 2077 | — |
| 143 | Tomb Raider | — |
| 112 | Average FPS | — |
| 135 | 1080p High | — |
| 112 | 1080p Ultra | — |
| 83 | 1440p Ultra | — |
| 47 | 4K Ultra | — |
| Low | Margin of Error | — |
| 133659 | GB6 Compute Score | 5099 |
| 200.9 img/sec | Background Blur | 12 img/sec |
| 131.2 img/sec | Face Detection | 6.42 img/sec |
| 6.49 Gpixels/sec | Horizon Detection | 0.16 Gpixels/sec |
| 8.9 Gpixels/sec | Edge Detection | 0.23 Gpixels/sec |
| 6.34 Gpixels/sec | Gaussian Blur | 0.16 Gpixels/sec |
| 1.2 Gpixels/sec | Feature Matching | 0.07 Gpixels/sec |
| 571 Gpixels/sec | Stereo Matching | 18.2 Gpixels/sec |
| 17240.3 FPS | Particle Physics | 828.6 FPS |
| OpenCL | API | OpenCL |
| 18948 | G3D Mark Score | 1810 |
| 817 | G2D Mark | 536 |
| 161 FPS | DirectX 11 | 17 FPS |
| 87 FPS | DirectX 12 | 7 FPS |
| 8302 Ops/s | GPU Compute | 771 Ops/s |
| 18415 | GB6 ML Single Precision | 1917 |
| 29828 | GB6 ML Half Precision | 2053 |
| 11425 | GB6 ML Quantized | 1571 |
| 6797 | Image Classification (SP) | 660 |
| 20808 | Image Segmentation (HP) | 627 |
| 15194 | Image Super Resolution (Q) | 2053 |
| 37084 | Face Detection (HP) | 2153 |
| 82268 | Pose Estimation (Q) | 5787 |
| 2863 | Text Classification (SP) | 713 |
| 4135 | Machine Translation (HP) | 1114 |
| 8559 | Object Detection (SP) | 709 |
| 28330 | Depth Estimation (Q) | 3233 |
| 184129 | Style Transfer (SP) | 11091 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 108-153 GPixel/s | Pixel Fill Rate | 8-9 GPixel/s |
| 261-369 GTexel/s | Texture Fill Rate | 15-18 GTexel/s |
| 16.7-23.6 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 | — |
| 256-bit | Bus | — |
| No | ECC | No |
| 512 GB/s | Memory Bandwidth | — |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 80-175 W (configurable) | TGP | 15 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 6 nm |
| 496 mm² | Die Size | 122 mm² |
| 22 billion | Transistor Count | 3.4 billion |
| 44.35 MTr/mm² | Transistor Density | 27.87 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 8.6 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 1, 2022 | Released | October 1, 2022 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Ampere | Architecture | RDNA 2.0 |
| GA103 (GN20-E8) | GPU Codename | Mendocino |
| -Intel Core i9 12900Hor above | Recommended CPU | -AMD Ryzen 5 7520Uor above |
| 12913 | Steel Nomad Lite Score | 447 |
| 12864 | Time Spy | 519 |
| 56305 | Solar Bay | 2078 |
| 8092 | Port Royal | 309 |
| 30858 | Fire Strike | 1760 |
| 26307 | Wild Life Extreme | 994 |
| 98582 | Night Raid | 7447 |
| 585-1230 MHz (configurable) | Base Clock | 400 MHz |
| 1125-1590 MHz (configurable) | Boost Clock | 1900-2200 MHz (configurable) |
| 7424 | Shading Units | 128 |
| 232 | Texture Mapping Units (TMUs) | 8 |
| 96 | Render Output Units (ROPs) | 4 |
| 58 | Compute Units (Pipelines) | 2 |
| 232 | Tensor Cores | — |
| 58 | Ray-tracing Cores | 2 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |