Quick/Comparisons
55 | Gaming | 51 |
56 | Workstation | 62 |
43 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →| — |
35 | Energy Efficiency | 49 |
54 | Quick Comparison Final Score | — |
| GA102 | Graphics Processor | BMG-G31 |
| 8704 | Cores | 4096 |
| 272 / 96 | TMUs / ROPs | 256 / 128 |
| 4812.92 | Blender GPU | 3324.51 |
| 114 | Forza Horizon 5 | — |
| 163 | The Witcher 3 | — |
| 205 | Counter-Strike 2 | — |
| 137 | Far Cry 6 | — |
| 97 | Hogwarts Legacy | — |
| 146 | Call of Duty | — |
| 90 | Ghost of Tsushima | — |
| 121 | Cyberpunk 2077 | — |
| 193 | Tomb Raider | — |
| 141 | Average FPS | — |
| 167 | 1080p High | — |
| 141 | 1080p Ultra | — |
| 109 | 1440p Ultra | — |
| 63 | 4K Ultra | — |
| Low | Margin of Error | — |
| 161903 | GB6 Compute Score | 179586 |
| 217.3 img/sec | Background Blur | — |
| 141.9 img/sec | Face Detection | — |
| 8.19 Gpixels/sec | Horizon Detection | — |
| 11 Gpixels/sec | Edge Detection | — |
| 8.43 Gpixels/sec | Gaussian Blur | — |
| 1.29 Gpixels/sec | Feature Matching | — |
| 780.7 Gpixels/sec | Stereo Matching | — |
| 22538.5 FPS | Particle Physics | — |
| OpenCL | API | — |
| 25030 | G3D Mark Score | 17577 |
| 1062 | G2D Mark | 601 |
| 207 FPS | DirectX 11 | 138 FPS |
| 100 FPS | DirectX 12 | 96 FPS |
| 14154 Ops/s | GPU Compute | 8261 Ops/s |
| 25471 | Image Segmentation (HP) | — |
| 19892 | Image Super Resolution (Q) | — |
| 46956 | Face Detection (HP) | — |
| 104704 | Pose Estimation (Q) | — |
| 2712 | Text Classification (SP) | — |
| 4828 | Machine Translation (HP) | — |
| 12153 | Object Detection (SP) | — |
| 36822 | Depth Estimation (Q) | — |
| 246005 | Style Transfer (SP) | — |
| ONNX | Framework | — |
| DirectML | Backend | — |
| 24003 | GB6 ML Single Precision | — |
| 36895 | GB6 ML Half Precision | — |
| 14629 | GB6 ML Quantized | — |
| 9439 | Image Classification (SP) | — |
| 164 GPixel/s | Pixel Fill Rate | 358 GPixel/s |
| 465 GTexel/s | Texture Fill Rate | 717 GTexel/s |
| 29.8 TFLOPS | FLOPS (FP32) | 22.9 TFLOPS |
| GDDR6X | Memory Type | GDDR6 |
| 10 GB | Memory Size | 32 GB |
| 1188 MHz | Memory Clock | 2375 MHz |
| 19000 Mbps | Effective Memory Speed | 19000 Mbps |
| 320-bit | Bus | 256-bit |
| No | ECC | No |
| 760.3 GB/s | Memory Bandwidth | 608 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 320 W | TGP | 230 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 628 mm² | Die Size | — |
| 28 billion | Transistor Count | — |
| 44.59 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1a |
| Nvidia | Vendor | Intel |
| Discrete | Build | Discrete |
| September 1, 2020 | Released | March 25, 2026 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Ampere | Architecture | Battlemage Pro Series |
| GA102 | GPU Codename | BMG-G31 |
| -Intel Core i7 12700Kor above | Recommended CPU | — |
| 19046 | Steel Nomad Lite Score | — |
| 17664 | Time Spy | 19094 |
| 85890 | Solar Bay | — |
| 11597 | Port Royal | — |
| 42468 | Fire Strike | 47615 |
| 37899 | Wild Life Extreme | — |
| 132892 | Night Raid | — |
| 1440 MHz | Base Clock | 2280 MHz |
| 1710 MHz | Boost Clock | 2800 MHz |
| 8704 | Shading Units | 4096 |
| 272 | Texture Mapping Units (TMUs) | 256 |
| 96 | Render Output Units (ROPs) | 128 |
| 68 | Compute Units (Pipelines) | 32 |
| 272 | Tensor Cores | 256 |
| 68 | Ray-tracing Cores | 32 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 5MB shared | L2 Cache | 16MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |