Quick/Comparisons
37 | Gaming | 5 |
42 | Workstation | 11 |
32 | AI/ML |
Compare with something else?
Compare GeForce RTX 2080 with another →4 |
27 | Energy Efficiency | 89 |
38 | Quick Comparison Final Score | 20 |
| TU104 | Graphics Processor | Mendocino |
| 3072 | Cores | 128 |
| 192 / 64 | TMUs / ROPs | 8 / 4 |
| 2407.76 | Blender GPU | 47.24 |
| 86 | Forza Horizon 5 | — |
| 121 | The Witcher 3 | — |
| 169 | Counter-Strike 2 | — |
| 105 | Far Cry 6 | — |
| 68 | Hogwarts Legacy | — |
| 97 | Call of Duty | — |
| 64 | Ghost of Tsushima | — |
| 82 | Cyberpunk 2077 | — |
| 131 | Tomb Raider | — |
| 103 | Average FPS | — |
| 124 | 1080p High | — |
| 103 | 1080p Ultra | — |
| 75 | 1440p Ultra | — |
| 42 | 4K Ultra | — |
| Low | Margin of Error | — |
| 122905 | GB6 Compute Score | 5099 |
| 197.1 img/sec | Background Blur | 12 img/sec |
| 110.7 img/sec | Face Detection | 6.42 img/sec |
| 5.03 Gpixels/sec | Horizon Detection | 0.16 Gpixels/sec |
| 6.5 Gpixels/sec | Edge Detection | 0.23 Gpixels/sec |
| 7.05 Gpixels/sec | Gaussian Blur | 0.16 Gpixels/sec |
| 1.28 Gpixels/sec | Feature Matching | 0.07 Gpixels/sec |
| 576.8 Gpixels/sec | Stereo Matching | 18.2 Gpixels/sec |
| 15732.9 FPS | Particle Physics | 828.6 FPS |
| OpenCL | API | OpenCL |
| 19452 | G3D Mark Score | 1810 |
| 919 | G2D Mark | 536 |
| 167 FPS | DirectX 11 | 17 FPS |
| 75 FPS | DirectX 12 | 7 FPS |
| 8204 Ops/s | GPU Compute | 771 Ops/s |
| 16090 | GB6 ML Single Precision | 1917 |
| 26121 | GB6 ML Half Precision | 2053 |
| 10870 | GB6 ML Quantized | 1571 |
| 6780 | Image Classification (SP) | 660 |
| 15029 | Image Segmentation (HP) | 627 |
| 15410 | Image Super Resolution (Q) | 2053 |
| 30849 | Face Detection (HP) | 2153 |
| 71857 | Pose Estimation (Q) | 5787 |
| 1983 | Text Classification (SP) | 713 |
| 3417 | Machine Translation (HP) | 1114 |
| 8214 | Object Detection (SP) | 709 |
| 26815 | Depth Estimation (Q) | 3233 |
| 148497 | Style Transfer (SP) | 11091 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 116 GPixel/s | Pixel Fill Rate | 8-9 GPixel/s |
| 348 GTexel/s | Texture Fill Rate | 15-18 GTexel/s |
| 11.2 TFLOPS | FLOPS (FP32) | 0.5-0.6 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1937 MHz | Memory Clock | — |
| 15500 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | No |
| 495.9 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x8 |
| 250 W | TGP | 15 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 6 nm |
| 545 mm² | Die Size | 122 mm² |
| 13 billion | Transistor Count | 3.4 billion |
| 23.85 MTr/mm² | Transistor Density | 27.87 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2 |
| 7.5 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| July 23, 2019 | Released | October 1, 2022 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Turing | Architecture | RDNA 2.0 |
| TU104 | GPU Codename | Mendocino |
| -Intel Core i9 9900Kor above | Recommended CPU | -AMD Ryzen 5 7520Uor above |
| 11569 | Steel Nomad Lite Score | 447 |
| 11621 | Time Spy | 519 |
| 52083 | Solar Bay | 2078 |
| 7001 | Port Royal | 309 |
| 28788 | Fire Strike | 1760 |
| 23792 | Wild Life Extreme | 994 |
| 108111 | Night Raid | 7447 |
| 1650 MHz | Base Clock | 400 MHz |
| 1815 MHz | Boost Clock | 1900-2200 MHz (configurable) |
| 3072 | Shading Units | 128 |
| 192 | Texture Mapping Units (TMUs) | 8 |
| 64 | Render Output Units (ROPs) | 4 |
| 48 | Compute Units (Pipelines) | 2 |
| 384 | Tensor Cores | — |
| 48 | Ray-tracing Cores | 2 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |