GeForce RTX 3090 Ti
- Graphics Processor: GA102
- Cores: 10752
- TMUs / ROPs: 336 / 112
Review
Compare GeForce RTX 3090 Ti with other GPUs
Games
| Forza Horizon 5 | 200 136 126 99 |
| The Witcher 3 | 214 185 130 71 |
| Counter-Strike 2 | 286 213 154 85 |
| Far Cry 6 | 160 151 133 83 |
| Hogwarts Legacy | 141 116 93 52 |
| CoD: Modern Warfare III | 186 174 139 90 |
| Ghost of Tsushima | 129 105 89 57 |
| Cyberpunk 2077 | 158 140 98 44 |
| Shadow of the Tomb Raider | 254 237 183 101 |
| 1080p High | 192 |
| 1080p Ultra | 162 |
| 1440p Ultra | 127 |
| 4K Ultra | 76 |
| Margin of Error | Low |
Test in Benchmarks
Performance tests in graphics benchmarks and applications3D Mark
| Time Spy | 21855 |
| Solar Bay | 109239 |
| Port Royal | 14890 |
| Fire Strike | 51935 |
| Wild Life Extreme | 48861 |
| Night Raid | 156537 |
GeekBench 6 OpenCL
| Background Blur | 362.7 img/sec |
| Face Detection | 227.9 img/sec |
| Horizon Detection | 11.3 Gpixels/sec |
| Edge Detection | 15.9 Gpixels/sec |
| Gaussian Blur | 12.1 Gpixels/sec |
| Feature Matching | 1.56 Gpixels/sec |
| Stereo Matching | 1080 Gpixels/sec |
| Particle Physics | 31024.6 FPS |
| API | OpenCL |
Cinebench 2024 GPU
Passmark Graphics
| G2D Mark | 1226 |
| DirectX 11 | 238 FPS |
| DirectX 12 | 121 FPS |
| GPU Compute | 16494 Ops/s |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
| Image Classification (SP) | 10246 |
| Image Segmentation (HP) | 22830 |
| Image Super Resolution (Q) | 23532 |
| Face Detection (HP) | 48657 |
| Pose Estimation (Q) | 147241 |
| Text Classification (SP) | 2917 |
| Machine Translation (HP) | 4427 |
| Object Detection (SP) | 13323 |
| Depth Estimation (Q) | 40055 |
| Style Transfer (SP) | 298683 |
| Framework | ONNX |
| Backend | DirectML |
Specifications
Detailed technical specifications of the GeForce RTX 3090 TiGeneral
| Vendor | Nvidia |
| Build | Discrete |
| Released | March 29, 2022 |
| Launch price (MSRP) | $1999 |
| Case | Desktop |
| Purpose | Gaming |
| Segment | High-end |
| Architecture | Ampere |
| GPU Codename | GA102 |
| Recommended CPU | - Intel Core i9 12900K or above |
Desktop GPU rating - 14th place
Graphics Processing Unit
| Base Clock | 1560 MHz |
| Boost Clock | 1860 MHz |
| Shading Units | 10752 |
| Texture Mapping Units (TMUs) | 336 |
| Render Output Units (ROPs) | 112 |
| Compute Units (Pipelines) | 84 |
| Tensor Cores | 336 |
| Ray-tracing Cores | 84 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 6MB shared |
| Instructions Per Cycle | 2 IPC |
Raw Performance
| Pixel Fill Rate | 208 GPixel/s |
| Texture Fill Rate | 625 GTexel/s |
Physical
| Interface | PCIe 4.0 x16 |
| TGP | 450 W |
| Manufacturing | Samsung |
| Fabrication Process | 8 nm |
| Die Size | 628 mm² |
| Transistor Count | 28 billion |
| Transistor Density | 44.59 MTr/mm² |
Memory
| Memory Type | GDDR6X |
| Memory Size | 24 GB |
| Memory Clock | 1313 MHz |
| Effective Memory Speed | 21000 Mbps |
| Bus | 384-bit |
| ECC | No |
API
| DirectX | 12 |
| Vulkan | 1.3 |
| OpenGL | 4.6 |
| OpenCL | 3.0 |
| CUDA | 8.6 |
| Ray Tracing | Yes |
| DLSS | DLSS 2 |
| DisplayPort | 1.4a |