Quick/Comparisons
39 | Gaming | 34 |
45 | Workstation | 41 |
35 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →38 |
39 | Energy Efficiency | 47 |
40 | Quick Comparison Final Score | 37 |
| GA104 (GN20-E7) | Graphics Processor | BMG-G21 |
| 6144 | Cores | 2560 |
| 192 / 96 | TMUs / ROPs | 160 / 80 |
| 3258.81 | Blender GPU | 2106.04 |
| 84 | Forza Horizon 5 | 78 |
| 127 | The Witcher 3 | 128 |
| 165 | Counter-Strike 2 | 116 |
| 104 | Far Cry 6 | 98 |
| 70 | Hogwarts Legacy | 57 |
| 98 | Call of Duty | 85 |
| 66 | Ghost of Tsushima | 61 |
| 84 | Cyberpunk 2077 | 82 |
| 129 | Tomb Raider | 107 |
| 103 | Average FPS | 90 |
| 125 | 1080p High | 109 |
| 103 | 1080p Ultra | 90 |
| 76 | 1440p Ultra | 67 |
| 44 | 4K Ultra | 38 |
| Low | Margin of Error | Low |
| 128827 | GB6 Compute Score | 111561 |
| 211 img/sec | Background Blur | 284.6 img/sec |
| 123.6 img/sec | Face Detection | 150 img/sec |
| 5.78 Gpixels/sec | Horizon Detection | 2.67 Gpixels/sec |
| 8.03 Gpixels/sec | Edge Detection | 5.22 Gpixels/sec |
| 6.25 Gpixels/sec | Gaussian Blur | 6.35 Gpixels/sec |
| 1.17 Gpixels/sec | Feature Matching | 1.18 Gpixels/sec |
| 543.2 Gpixels/sec | Stereo Matching | 397 Gpixels/sec |
| 17774.9 FPS | Particle Physics | 15177.3 FPS |
| OpenCL | API | OpenCL |
| 16147 | G3D Mark Score | 15914 |
| 630 | G2D Mark | 700 |
| 145 FPS | DirectX 11 | 126 FPS |
| 71 FPS | DirectX 12 | 77 FPS |
| 7126 Ops/s | GPU Compute | 7896 Ops/s |
| 18354 | GB6 ML Single Precision | 21661 |
| 29767 | GB6 ML Half Precision | 34463 |
| 11487 | GB6 ML Quantized | 14366 |
| 6773 | Image Classification (SP) | 10654 |
| 19587 | Image Segmentation (HP) | 18608 |
| 15553 | Image Super Resolution (Q) | 16715 |
| 35885 | Face Detection (HP) | 40348 |
| 82446 | Pose Estimation (Q) | 64494 |
| 2830 | Text Classification (SP) | 3091 |
| 4019 | Machine Translation (HP) | 3530 |
| 8380 | Object Detection (SP) | 13690 |
| 28597 | Depth Estimation (Q) | 36797 |
| 184715 | Style Transfer (SP) | 197057 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 120-164 GPixel/s | Pixel Fill Rate | 214 GPixel/s |
| 239-328 GTexel/s | Texture Fill Rate | 427 GTexel/s |
| 15.3-21 TFLOPS | FLOPS (FP32) | 13.7 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8-16 GB | Memory Size | 12 GB |
| 1500-1750 MHz | Memory Clock | 2375 MHz |
| 12000-14000 Mbps | Effective Memory Speed | 19000 Mbps |
| 256-bit | Bus | 192-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 456 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 80-165 W (configurable) | TGP | 190 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 392 mm² | Die Size | 272 mm² |
| 17.4 billion | Transistor Count | 19.6 billion |
| 44.39 MTr/mm² | Transistor Density | 72.06 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2 | OpenCL | 3 |
| 8.6 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Discrete |
| January 12, 2021 | Released | December 3, 2024 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Ampere | Architecture | Generation 12.7 |
| GA104 (GN20-E7) | GPU Codename | BMG-G21 |
| -Intel Core i9 12900Hor above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 11592 | Steel Nomad Lite Score | 11180 |
| 11991 | Time Spy | 14665 |
| 50371 | Solar Bay | 55557 |
| 7201 | Port Royal | 7919 |
| 29067 | Fire Strike | 36685 |
| 24760 | Wild Life Extreme | 28324 |
| 81949 | Night Raid | 123864 |
| 780-1350 MHz (configurable) | Base Clock | 1700 MHz |
| 1245-1710 MHz (configurable) | Boost Clock | 2670 MHz |
| 6144 | Shading Units | 2560 |
| 192 | Texture Mapping Units (TMUs) | 160 |
| 96 | Render Output Units (ROPs) | 80 |
| 48 | Compute Units (Pipelines) | 20 |
| 192 | Tensor Cores | 160 |
| 48 | Ray-tracing Cores | 20 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 4MB shared | L2 Cache | 12MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |