GeForce RTX 2080 Ti
- Graphics Processor: TU102
- Cores: 4352
- TMUs / ROPs: 272 / 88
Review
Compare GeForce RTX 2080 Ti with other GPUs
Games
| Forza Horizon 5 | 150 101 89 65 |
| The Witcher 3 | 175 142 104 55 |
| Counter-Strike 2 | 253 193 140 81 |
| Far Cry 6 | 132 122 101 61 |
| Hogwarts Legacy | 101 85 65 36 |
| CoD: Modern Warfare III | 124 117 85 56 |
| Ghost of Tsushima | 92 79 61 36 |
| Cyberpunk 2077 | 112 96 63 30 |
| Shadow of the Tomb Raider | 171 161 120 63 |
| 1080p High | 146 |
| 1080p Ultra | 122 |
| 1440p Ultra | 92 |
| 4K Ultra | 54 |
| Margin of Error | Low |
Test in Benchmarks
Performance tests in graphics benchmarks and applications3D Mark
| Time Spy | 14655 |
| Solar Bay | 64022 |
| Port Royal | 9109 |
| Fire Strike | 35666 |
| Wild Life Extreme | 29561 |
| Night Raid | 115542 |
GeekBench 6 OpenCL
| Background Blur | 211 img/sec |
| Face Detection | 141.3 img/sec |
| Horizon Detection | 6.24 Gpixels/sec |
| Edge Detection | 8.1 Gpixels/sec |
| Gaussian Blur | 9.22 Gpixels/sec |
| Feature Matching | 1.46 Gpixels/sec |
| Stereo Matching | 627.3 Gpixels/sec |
| Particle Physics | 16980.5 FPS |
| API | OpenCL |
Cinebench 2024 GPU
Passmark Graphics
| G2D Mark | 926 |
| DirectX 11 | 193 FPS |
| DirectX 12 | 83 FPS |
| GPU Compute | 9831 Ops/s |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
| Image Classification (SP) | 8213 |
| Image Segmentation (HP) | 19891 |
| Image Super Resolution (Q) | 17598 |
| Face Detection (HP) | 39785 |
| Pose Estimation (Q) | 84003 |
| Text Classification (SP) | 2062 |
| Machine Translation (HP) | 4192 |
| Object Detection (SP) | 10444 |
| Depth Estimation (Q) | 31856 |
| Style Transfer (SP) | 207773 |
| Framework | ONNX |
| Backend | DirectML |
Specifications
Detailed technical specifications of the GeForce RTX 2080 TiGeneral
| Vendor | Nvidia |
| Build | Discrete |
| Released | September 27, 2018 |
| Launch price (MSRP) | $999 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | High-end |
| Architecture | Turing |
| GPU Codename | TU102 |
| Successor | - GeForce RTX 3080 Ti |
| Recommended CPU | - Intel Core i9 9900K or above |
Desktop GPU rating - 40th place
Graphics Processing Unit
| Base Clock | 1350 MHz |
| Boost Clock | 1545 MHz |
| Shading Units | 4352 |
| Texture Mapping Units (TMUs) | 272 |
| Render Output Units (ROPs) | 88 |
| Compute Units (Pipelines) | 68 |
| Tensor Cores | 544 |
| Ray-tracing Cores | 68 |
| L1 Cache | 64KB per cluster |
| L2 Cache | 5632KB shared |
| Instructions Per Cycle | 2 IPC |
Raw Performance
| Pixel Fill Rate | 136 GPixel/s |
| Texture Fill Rate | 420 GTexel/s |
Physical
| Interface | PCIe 3.0 x16 |
| TGP | 250 W |
| Manufacturing | TSMC |
| Fabrication Process | 12 nm |
| Die Size | 754 mm² |
| Transistor Count | 18 billion |
| Transistor Density | 23.87 MTr/mm² |
Memory
| Memory Type | GDDR6 |
| Memory Size | 11 GB |
| Memory Clock | 1750 MHz |
| Effective Memory Speed | 14000 Mbps |
| Bus | 352-bit |
| ECC | No |
API
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3.0 |
| CUDA | 7.5 |
| Ray Tracing | Yes |
| DLSS | DLSS 2 |
| DisplayPort | 1.4a |