Quick/Comparisons
60 | Gaming | 61 |
64 | Workstation | 69 |
46 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →53 |
35 | Energy Efficiency | 35 |
59 | Quick Comparison Final Score | 62 |
| GA102 | Graphics Processor | GA102 |
| 10240 | Cores | 10496 |
| 320 / 112 | TMUs / ROPs | 328 / 112 |
| 5565.9 | Blender GPU | 5800.59 |
| 128 | Forza Horizon 5 | 125 |
| 174 | The Witcher 3 | 175 |
| 205 | Counter-Strike 2 | 212 |
| 139 | Far Cry 6 | 142 |
| 108 | Hogwarts Legacy | 106 |
| 161 | Call of Duty | 159 |
| 96 | Ghost of Tsushima | 97 |
| 128 | Cyberpunk 2077 | 132 |
| 219 | Tomb Raider | 226 |
| 151 | Average FPS | 153 |
| 180 | 1080p High | 179 |
| 151 | 1080p Ultra | 153 |
| 117 | 1440p Ultra | 119 |
| 69 | 4K Ultra | 70 |
| Low | Margin of Error | Low |
| 196756 | GB6 Compute Score | 211669 |
| 239.8 img/sec | Background Blur | 320.8 img/sec |
| 156.8 img/sec | Face Detection | 207.2 img/sec |
| 10.8 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 14.8 Gpixels/sec | Edge Detection | 14.4 Gpixels/sec |
| 11.9 Gpixels/sec | Gaussian Blur | 11.5 Gpixels/sec |
| 1.53 Gpixels/sec | Feature Matching | 1.48 Gpixels/sec |
| 889.6 Gpixels/sec | Stereo Matching | 984.2 Gpixels/sec |
| 26054.6 FPS | Particle Physics | 27764.9 FPS |
| OpenCL | API | OpenCL |
| 26777 | G3D Mark Score | 26551 |
| 1095 | G2D Mark | 1069 |
| 222 FPS | DirectX 11 | 218 FPS |
| 109 FPS | DirectX 12 | 110 FPS |
| 15025 Ops/s | GPU Compute | 15117 Ops/s |
| 25945 | GB6 ML Single Precision | 27237 |
| 38430 | GB6 ML Half Precision | 41500 |
| 15331 | GB6 ML Quantized | 15927 |
| 9747 | Image Classification (SP) | 10665 |
| 26654 | Image Segmentation (HP) | 28963 |
| 21475 | Image Super Resolution (Q) | 22697 |
| 49813 | Face Detection (HP) | 55232 |
| 135370 | Pose Estimation (Q) | 128155 |
| 2796 | Text Classification (SP) | 3152 |
| 4757 | Machine Translation (HP) | 5088 |
| 12924 | Object Detection (SP) | 13891 |
| 36756 | Depth Estimation (Q) | 37984 |
| 274032 | Style Transfer (SP) | 272000 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 186 GPixel/s | Pixel Fill Rate | 190 GPixel/s |
| 533 GTexel/s | Texture Fill Rate | 556 GTexel/s |
| 34.1 TFLOPS | FLOPS (FP32) | 35.6 TFLOPS |
| GDDR6X | Memory Type | GDDR6X |
| 12 GB | Memory Size | 24 GB |
| 1188 MHz | Memory Clock | 1219 MHz |
| 19000 Mbps | Effective Memory Speed | 19500 Mbps |
| 384-bit | Bus | 384-bit |
| No | ECC | No |
| 912 GB/s | Memory Bandwidth | 936.2 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 350 W | TGP | 350 W |
| Samsung | Manufacturing | Samsung |
| 8 nm | Fabrication Process | 8 nm |
| 628 mm² | Die Size | 628 mm² |
| 28 billion | Transistor Count | 28 billion |
| 44.59 MTr/mm² | Transistor Density | 44.59 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 2 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 3, 2021 | Released | September 24, 2020 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | Ampere |
| GA102 | GPU Codename | GA102 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i9 12900Kor above |
| 21408 | Steel Nomad Lite Score | 21851 |
| 19632 | Time Spy | 19896 |
| 96597 | Solar Bay | 97375 |
| 13265 | Port Royal | 13631 |
| 47867 | Fire Strike | 47515 |
| 42716 | Wild Life Extreme | 43673 |
| 144955 | Night Raid | 139755 |
| 1365 MHz | Base Clock | 1395 MHz |
| 1665 MHz | Boost Clock | 1695 MHz |
| 10240 | Shading Units | 10496 |
| 320 | Texture Mapping Units (TMUs) | 328 |
| 112 | Render Output Units (ROPs) | 112 |
| 80 | Compute Units (Pipelines) | 82 |
| 320 | Tensor Cores | 328 |
| 80 | Ray-tracing Cores | 82 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 6MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |