Quick/Comparisons
60 | Gaming | 10 |
64 | Workstation | 21 |
46 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →9 |
35 | Energy Efficiency | 73 |
59 | Quick Comparison Final Score | 23 |
| GA102 | Graphics Processor | TU117 |
| 10240 | Cores | 1024 |
| 320 / 112 | TMUs / ROPs | 64 / 32 |
| 5565.9 | Blender GPU | 142.83 |
| 128 | Forza Horizon 5 | — |
| 174 | The Witcher 3 | — |
| 205 | Counter-Strike 2 | — |
| 139 | Far Cry 6 | — |
| 108 | Hogwarts Legacy | — |
| 161 | Call of Duty | — |
| 96 | Ghost of Tsushima | — |
| 128 | Cyberpunk 2077 | — |
| 219 | Tomb Raider | — |
| 151 | Average FPS | — |
| 180 | 1080p High | — |
| 151 | 1080p Ultra | — |
| 117 | 1440p Ultra | — |
| 69 | 4K Ultra | — |
| Low | Margin of Error | — |
| 196756 | GB6 Compute Score | 35511 |
| 239.8 img/sec | Background Blur | 61.9 img/sec |
| 156.8 img/sec | Face Detection | 28.6 img/sec |
| 10.8 Gpixels/sec | Horizon Detection | 1.2 Gpixels/sec |
| 14.8 Gpixels/sec | Edge Detection | 1.67 Gpixels/sec |
| 11.9 Gpixels/sec | Gaussian Blur | 1.9 Gpixels/sec |
| 1.53 Gpixels/sec | Feature Matching | 0.5 Gpixels/sec |
| 889.6 Gpixels/sec | Stereo Matching | 174.2 Gpixels/sec |
| 26054.6 FPS | Particle Physics | 4869.6 FPS |
| OpenCL | API | OpenCL |
| 26777 | G3D Mark Score | 4752 |
| 1095 | G2D Mark | 401 |
| 222 FPS | DirectX 11 | 35 FPS |
| 109 FPS | DirectX 12 | 30 FPS |
| 15025 Ops/s | GPU Compute | 2256 Ops/s |
| 25945 | GB6 ML Single Precision | 4976 |
| 38430 | GB6 ML Half Precision | 4623 |
| 15331 | GB6 ML Quantized | 3647 |
| 9747 | Image Classification (SP) | 2063 |
| 26654 | Image Segmentation (HP) | 3228 |
| 21475 | Image Super Resolution (Q) | 4420 |
| 49813 | Face Detection (HP) | 5053 |
| 135370 | Pose Estimation (Q) | 14361 |
| 2796 | Text Classification (SP) | 1515 |
| 4757 | Machine Translation (HP) | 2212 |
| 12924 | Object Detection (SP) | 2394 |
| 36756 | Depth Estimation (Q) | 8645 |
| 274032 | Style Transfer (SP) | 33780 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 186 GPixel/s | Pixel Fill Rate | 53 GPixel/s |
| 533 GTexel/s | Texture Fill Rate | 107 GTexel/s |
| 34.1 TFLOPS | FLOPS (FP32) | 3.4 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 12 GB | Memory Size | 4 GB |
| 1188 MHz | Memory Clock | 1500 MHz |
| 19000 Mbps | Effective Memory Speed | 12000 Mbps |
| 384-bit | Bus | 64-bit |
| No | ECC | No |
| 912 GB/s | Memory Bandwidth | 96 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 3.0 x16 |
| 350 W | TGP | 30 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 12 nm |
| 628 mm² | Die Size | 200 mm² |
| 28 billion | Transistor Count | 4.7 billion |
| 44.59 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 |
| January 3, 2021 | Released | May 1, 2022 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| High-end | Segment | Entry-level |
| Ampere | Architecture | Turing |
| GA102 | GPU Codename | TU117 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core i7 1265Uor above |
| 21408 | Steel Nomad Lite Score | 1984 |
| 19632 | Time Spy | 2273 |
| 96597 | Solar Bay | — |
| 13265 | Port Royal | — |
| 47867 | Fire Strike | 5443 |
| 42716 | Wild Life Extreme | 4481 |
| 144955 | Night Raid | 28589 |
| 1365 MHz | Base Clock | 1065 MHz |
| 1665 MHz | Boost Clock | 1665 MHz |
| 10240 | Shading Units | 1024 |
| 320 | Texture Mapping Units (TMUs) | 64 |
| 112 | Render Output Units (ROPs) | 32 |
| 80 | Compute Units (Pipelines) | 16 |
| 320 | Tensor Cores | — |
| 80 | Ray-tracing Cores | — |
| 128KB per cluster | L1 Cache | 64KB per cluster |
| 6MB shared | L2 Cache | 1MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |