Quick/Comparisons
The GeForce RTX 2080 Ti dominates in gaming with a score of 44, thanks to its Turing architecture and 11GB GDDR6 memory.
The GeForce RTX 2080 Ti takes the lead in content creation with a score of 48, leveraging its dedicated AI tensor cores and TU102 codename.
The GeForce RTX 2080 Ti excels in AI & Machine Learning with a score of 39, utilizing its dedicated AI tensor cores and Turing architecture.
44 | Gaming | 2 |
48 | Workstation | 7 |
39 | AI/ML |
Compare with something else?
Compare GeForce RTX 2080 with another →2 |
27 | Energy Efficiency | 79 |
44 | Quick Comparison Final Score | 16 |
| TU102 | Graphics Processor | Ice Lake G1 Gen. 11 |
| 4352 | Cores | 256 |
| 272 / 88 | TMUs / ROPs | 16 / 8 |
| 3046.64 | Blender GPU | — |
| 101 | Forza Horizon 5 | — |
| 144 | The Witcher 3 | — |
| 199 | Counter-Strike 2 | — |
| 122 | Far Cry 6 | — |
| 82 | Hogwarts Legacy | — |
| 118 | Call of Duty | — |
| 78 | Ghost of Tsushima | — |
| 98 | Cyberpunk 2077 | — |
| 155 | Tomb Raider | — |
| 122 | Average FPS | — |
| 145 | 1080p High | — |
| 122 | 1080p Ultra | — |
| 92 | 1440p Ultra | — |
| 52 | 4K Ultra | — |
| Low | Margin of Error | — |
| 144745 | GB6 Compute Score | 4800 |
| 211 img/sec | Background Blur | 9.94 img/sec |
| 141.3 img/sec | Face Detection | 5.9 img/sec |
| 6.24 Gpixels/sec | Horizon Detection | 0.18 Gpixels/sec |
| 8.1 Gpixels/sec | Edge Detection | 0.24 Gpixels/sec |
| 9.22 Gpixels/sec | Gaussian Blur | 0.19 Gpixels/sec |
| 1.46 Gpixels/sec | Feature Matching | 0.05 Gpixels/sec |
| 627.3 Gpixels/sec | Stereo Matching | 14 Gpixels/sec |
| 16980.5 FPS | Particle Physics | 852 FPS |
| OpenCL | API | OpenCL |
| 21477 | G3D Mark Score | 1384 |
| 927 | G2D Mark | 324 |
| 192 FPS | DirectX 11 | 11 FPS |
| 83 FPS | DirectX 12 | 6 FPS |
| 9906 Ops/s | GPU Compute | 813 Ops/s |
| 19878 | GB6 ML Single Precision | 842 |
| 31237 | GB6 ML Half Precision | 916 |
| 12663 | GB6 ML Quantized | 637 |
| 8213 | Image Classification (SP) | 325 |
| 19891 | Image Segmentation (HP) | 598 |
| 17598 | Image Super Resolution (Q) | 884 |
| 39785 | Face Detection (HP) | 821 |
| 84003 | Pose Estimation (Q) | 2386 |
| 2062 | Text Classification (SP) | 274 |
| 4192 | Machine Translation (HP) | 333 |
| 10444 | Object Detection (SP) | 369 |
| 31856 | Depth Estimation (Q) | 1290 |
| 207773 | Style Transfer (SP) | 6941 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 136 GPixel/s | Pixel Fill Rate | 7-8 GPixel/s |
| 420 GTexel/s | Texture Fill Rate | 14-17 GTexel/s |
| 13.4 TFLOPS | FLOPS (FP32) | 0.5 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 11 GB | Memory Size | System RAM Dependent |
| 1750 MHz | Memory Clock | System RAM Dependent |
| 14000 Mbps | Effective Memory Speed | System RAM Dependent |
| 352-bit | Bus | — |
| No | ECC | — |
| 616 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | Ring Bus |
| 250 W | TGP | 15 W |
| TSMC | Manufacturing | Intel |
| 12 nm | Fabrication Process | 10 nm |
| 754 mm² | Die Size | — |
| 18 billion | Transistor Count | — |
| 23.87 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.5 |
| 3 | OpenCL | 2.2 |
| 7.5 | CUDA | — |
| Yes | Ray Tracing | — |
| DLSS 2 | DLSS | — |
| 1.4a | DisplayPort | — |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| September 27, 2018 | Released | May 28, 2019 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Turing | Architecture | Generation 11 |
| TU102 | GPU Codename | Ice Lake G1 Gen. 11 |
| -Intel Core i9 9900Kor above | Recommended CPU | -Intel Core i3 1005G1or above |
| 14284 | Steel Nomad Lite Score | 336 |
| 14656 | Time Spy | 386 |
| 64076 | Solar Bay | — |
| 9109 | Port Royal | — |
| 35666 | Fire Strike | 1175 |
| 29554 | Wild Life Extreme | 819 |
| 115500 | Night Raid | 5442 |
| 1350 MHz | Base Clock | 300 MHz |
| 1545 MHz | Boost Clock | 900-1050 MHz (configurable) |
| 4352 | Shading Units | 256 |
| 272 | Texture Mapping Units (TMUs) | 16 |
| 88 | Render Output Units (ROPs) | 8 |
| 68 | Compute Units (Pipelines) | 32 |
| 544 | Tensor Cores | — |
| 68 | Ray-tracing Cores | — |
| 64KB per cluster | L1 Cache | — |
| 5632KB shared | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |