Quick/Comparisons
39 | Gaming | 63 |
45 | Workstation | 63 |
35 | AI/ML |
Compare with something else?
Compare GeForce RTX 3080 with another →55 |
39 | Energy Efficiency | 45 |
40 | Quick Comparison Final Score | 59 |
| GA104 (GN20-E7) | Graphics Processor | AD103 (GN21-X11) |
| 6144 | Cores | 9728 |
| 192 / 96 | TMUs / ROPs | 304 / 112 |
| 3258.81 | Blender GPU | 7059.06 |
| 84 | Forza Horizon 5 | 131 |
| 127 | The Witcher 3 | 182 |
| 165 | Counter-Strike 2 | 208 |
| 104 | Far Cry 6 | 147 |
| 70 | Hogwarts Legacy | 108 |
| 98 | Call of Duty | 164 |
| 66 | Ghost of Tsushima | 100 |
| 84 | Cyberpunk 2077 | 137 |
| 129 | Tomb Raider | 231 |
| 103 | Average FPS | 156 |
| 125 | 1080p High | 187 |
| 103 | 1080p Ultra | 156 |
| 76 | 1440p Ultra | 123 |
| 44 | 4K Ultra | 72 |
| Low | Margin of Error | Low |
| 128827 | GB6 Compute Score | 203263 |
| 211 img/sec | Background Blur | 264 img/sec |
| 123.6 img/sec | Face Detection | 134.3 img/sec |
| 5.78 Gpixels/sec | Horizon Detection | 9.27 Gpixels/sec |
| 8.03 Gpixels/sec | Edge Detection | 12.7 Gpixels/sec |
| 6.25 Gpixels/sec | Gaussian Blur | 13.2 Gpixels/sec |
| 1.17 Gpixels/sec | Feature Matching | 1.92 Gpixels/sec |
| 543.2 Gpixels/sec | Stereo Matching | 1060 Gpixels/sec |
| 17774.9 FPS | Particle Physics | 29225.1 FPS |
| OpenCL | API | OpenCL |
| 16147 | G3D Mark Score | 27060 |
| 630 | G2D Mark | 988 |
| 145 FPS | DirectX 11 | 258 FPS |
| 71 FPS | DirectX 12 | 106 FPS |
| 7126 Ops/s | GPU Compute | 12206 Ops/s |
| 18354 | GB6 ML Single Precision | 29362 |
| 29767 | GB6 ML Half Precision | 42611 |
| 11487 | GB6 ML Quantized | 22212 |
| 6773 | Image Classification (SP) | 11346 |
| 19587 | Image Segmentation (HP) | 24625 |
| 15553 | Image Super Resolution (Q) | 36874 |
| 35885 | Face Detection (HP) | 50088 |
| 82446 | Pose Estimation (Q) | 174844 |
| 2830 | Text Classification (SP) | 3226 |
| 4019 | Machine Translation (HP) | 4905 |
| 8380 | Object Detection (SP) | 14667 |
| 28597 | Depth Estimation (Q) | 53868 |
| 184715 | Style Transfer (SP) | 340056 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 120-164 GPixel/s | Pixel Fill Rate | 163-228 GPixel/s |
| 239-328 GTexel/s | Texture Fill Rate | 442-620 GTexel/s |
| 15.3-21 TFLOPS | FLOPS (FP32) | 28.3-39.7 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8-16 GB | Memory Size | 16 GB |
| 1500-1750 MHz | Memory Clock | 2000 MHz |
| 12000-14000 Mbps | Effective Memory Speed | 16000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 512 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 80-165 W (configurable) | TGP | 80-175 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 5 nm |
| 392 mm² | Die Size | 379 mm² |
| 17.4 billion | Transistor Count | 45.9 billion |
| 44.39 MTr/mm² | Transistor Density | 121.11 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2 | 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 12, 2021 | Released | February 8, 2023 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ampere | Architecture | Ada Lovelace |
| GA104 (GN20-E7) | GPU Codename | AD103 (GN21-X11) |
| -Intel Core i9 12900Hor above | Recommended CPU | -Intel Core Ultra 9 185Hor above |
| 11592 | Steel Nomad Lite Score | 22501 |
| 11991 | Time Spy | 21401 |
| 50371 | Solar Bay | 96130 |
| 7201 | Port Royal | 13733 |
| 29067 | Fire Strike | 45218 |
| 24760 | Wild Life Extreme | 42491 |
| 81949 | Night Raid | 147892 |
| 780-1350 MHz (configurable) | Base Clock | 930-1620 MHz (configurable) |
| 1245-1710 MHz (configurable) | Boost Clock | 1455-2040 MHz (configurable) |
| 6144 | Shading Units | 9728 |
| 192 | Texture Mapping Units (TMUs) | 304 |
| 96 | Render Output Units (ROPs) | 112 |
| 48 | Compute Units (Pipelines) | 76 |
| 192 | Tensor Cores | 304 |
| 48 | Ray-tracing Cores | 76 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |