Quick/Comparisons
60 | Gaming | 70 |
64 | Workstation | 72 |
46 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →59 |
35 | Energy Efficiency | 46 |
59 | Quick Comparison Final Score | 69 |
| GA102 | Graphics Processor | AD103 |
| 10240 | Cores | 8448 |
| 320 / 112 | TMUs / ROPs | 264 / 96 |
| 5565.9 | Blender GPU | 7089.35 |
| 128 | Forza Horizon 5 | 150 |
| 174 | The Witcher 3 | 198 |
| 205 | Counter-Strike 2 | 220 |
| 139 | Far Cry 6 | 152 |
| 108 | Hogwarts Legacy | 118 |
| 161 | Call of Duty | 188 |
| 96 | Ghost of Tsushima | 111 |
| 128 | Cyberpunk 2077 | 155 |
| 219 | Tomb Raider | 249 |
| 151 | Average FPS | 171 |
| 180 | 1080p High | 200 |
| 151 | 1080p Ultra | 171 |
| 117 | 1440p Ultra | 134 |
| 69 | 4K Ultra | 79 |
| Low | Margin of Error | Low |
| 196756 | GB6 Compute Score | 237068 |
| 239.8 img/sec | Background Blur | 331.7 img/sec |
| 156.8 img/sec | Face Detection | 211.6 img/sec |
| 10.8 Gpixels/sec | Horizon Detection | 9.63 Gpixels/sec |
| 14.8 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 11.9 Gpixels/sec | Gaussian Blur | 13.9 Gpixels/sec |
| 1.53 Gpixels/sec | Feature Matching | 2.15 Gpixels/sec |
| 889.6 Gpixels/sec | Stereo Matching | 1210 Gpixels/sec |
| 26054.6 FPS | Particle Physics | 33566 FPS |
| OpenCL | API | OpenCL |
| 26777 | G3D Mark Score | 31798 |
| 1095 | G2D Mark | 1240 |
| 222 FPS | DirectX 11 | 277 FPS |
| 109 FPS | DirectX 12 | 119 FPS |
| 15025 Ops/s | GPU Compute | 18264 Ops/s |
| 25945 | GB6 ML Single Precision | 32793 |
| 38430 | GB6 ML Half Precision | 47412 |
| 15331 | GB6 ML Quantized | 24566 |
| 9747 | Image Classification (SP) | 12970 |
| 26654 | Image Segmentation (HP) | 26364 |
| 21475 | Image Super Resolution (Q) | 37217 |
| 49813 | Face Detection (HP) | 58720 |
| 135370 | Pose Estimation (Q) | 177604 |
| 2796 | Text Classification (SP) | 3815 |
| 4757 | Machine Translation (HP) | 5829 |
| 12924 | Object Detection (SP) | 15675 |
| 36756 | Depth Estimation (Q) | 62447 |
| 274032 | Style Transfer (SP) | 357918 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 186 GPixel/s | Pixel Fill Rate | 251 GPixel/s |
| 533 GTexel/s | Texture Fill Rate | 689 GTexel/s |
| 34.1 TFLOPS | FLOPS (FP32) | 44.1 TFLOPS |
| GDDR6X | Memory Type | GDDR6X |
| 12 GB | Memory Size | 16 GB |
| 1188 MHz | Memory Clock | 1313 MHz |
| 19000 Mbps | Effective Memory Speed | 21000 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | No |
| 912 GB/s | Memory Bandwidth | 672.3 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 350 W | TGP | 285 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | 379 mm² |
| 28 billion | Transistor Count | 45 billion |
| 44.59 MTr/mm² | Transistor Density | 118.73 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 3 |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 3, 2021 | Released | January 24, 2024 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA102 | GPU Codename | AD103 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i7 14700Kor above |
| 21408 | Steel Nomad Lite Score | 25741 |
| 19632 | Time Spy | 24222 |
| 96597 | Solar Bay | 116542 |
| 13265 | Port Royal | 15802 |
| 47867 | Fire Strike | 56340 |
| 42716 | Wild Life Extreme | 49901 |
| 144955 | Night Raid | 176609 |
| 1365 MHz | Base Clock | 2340 MHz |
| 1665 MHz | Boost Clock | 2610 MHz |
| 10240 | Shading Units | 8448 |
| 320 | Texture Mapping Units (TMUs) | 264 |
| 112 | Render Output Units (ROPs) | 96 |
| 80 | Compute Units (Pipelines) | 66 |
| 320 | Tensor Cores | 264 |
| 80 | Ray-tracing Cores | 66 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 6MB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |