Key Differences
Advantages of GeForce RTX 3080 Ti
Advantages of GeForce RTX 3090
Specifications
Performance
| TGP | 350 W | 350 W |
Storage Details
| Bus | 384-bit | 384-bit |
Ports
| DisplayPort | 1.4a | 1.4a |
Other
| Forza Horizon 5 | 18812811590 | 18812711891 |
| The Witcher 3 | 20716912667 | 20917512669 |
| Counter-Strike 2 | 27221515284 | 27421515685 |
| Far Cry 6 | 15413912277 | 15314512278 |
| Hogwarts Legacy | 1311078545 | 1271078747 |
| CoD: Modern Warfare III | 16915812282 | 17116412482 |
| Ghost of Tsushima | 119968150 | 120978248 |
| Cyberpunk 2077 | 1431318640 | 1511328939 |
| Shadow of the Tomb Raider | 23521916992 | 24221817290 |
| 1080p High | 180 | 182 |
| 1080p Ultra | 151 | 153 |
| 1440p Ultra | 118 | 120 |
| 4K Ultra | 70 | 70 |
| Margin of Error | Low | Low |
| Time Spy | 19631 | 19899 |
| Solar Bay | 96536 | 97411 |
| Port Royal | 13263 | 13633 |
| Fire Strike | 47874 | 47513 |
| Wild Life Extreme | 42703 | 43649 |
| Night Raid | 144403 | 139651 |
| Background Blur | 239.8 img/sec | 320.8 img/sec |
| Face Detection | 156.8 img/sec | 207.2 img/sec |
| Horizon Detection | 10.8 Gpixels/sec | 10.1 Gpixels/sec |
| Edge Detection | 14.8 Gpixels/sec | 14.4 Gpixels/sec |
| Gaussian Blur | 11.9 Gpixels/sec | 11.5 Gpixels/sec |
| Feature Matching | 1.53 Gpixels/sec | 1.48 Gpixels/sec |
| Stereo Matching | 889.6 Gpixels/sec | 984.2 Gpixels/sec |
| Particle Physics | 26054.6 FPS | 27764.9 FPS |
| API | OpenGL | OpenGL |
| G2D Mark | 1094 | 1066 |
| DirectX 11 | 222 FPS | 219 FPS |
| DirectX 12 | 110 FPS | 110 FPS |
| GPU Compute | 15154 Ops/s | 15243 Ops/s |
| Aztec Ruins Normal Tier | 1039 FPS | 978.4 FPS |
| Car Chase | 872 FPS | 854.1 FPS |
| Manhattan 3.1.1 (1440p) | 747.2 FPS | 747.4 FPS |
| T-Rex | 3834.2 FPS | 3732.1 FPS |
| Tessellation | 6622.8 FPS | 6622.8 FPS |
| ALU 2 | 6702 FPS | 6650.9 FPS |
| Driver Overhead 2 | 296.1 FPS | 296 FPS |
| OS | Windows | Windows |
| Image Classification (SP) | 9747 | 10665 |
| Image Segmentation (HP) | 26654 | 28963 |
| Image Super Resolution (Q) | 21475 | 22697 |
| Face Detection (HP) | 49813 | 55232 |
| Pose Estimation (Q) | 135370 | 128155 |
| Text Classification (SP) | 2796 | 3152 |
| Machine Translation (HP) | 4757 | 5088 |
| Object Detection (SP) | 12924 | 13891 |
| Depth Estimation (Q) | 36756 | 37984 |
| Style Transfer (SP) | 274032 | 272000 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 3, 2021 | September 24, 2020 |
| Launch price (MSRP) | $1199 | $1499 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Ampere | Ampere |
| GPU Codename | GA102 | GA102 |
| Rival Equivalent | Radeon RX 6900 XT | Radeon RX 6900 XT |
| Base Clock | 1365 MHz | 1395 MHz |
| Boost Clock | 1665 MHz | 1695 MHz |
| Shading Units | 10240 | 10496 |
| Texture Mapping Units (TMUs) | 320 | 328 |
| Render Output Units (ROPs) | 112 | 112 |
| Compute Units (Pipelines) | 80 | 82 |
| Tensor Cores | 320 | 328 |
| Ray-tracing Cores | 80 | 82 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 6MB shared | 6MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
| Pixel Fill Rate | 186 GPixel/s | 190 GPixel/s |
| Texture Fill Rate | 533 GTexel/s | 556 GTexel/s |
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Manufacturing | Samsung | Samsung |
| Fabrication Process | 8 nm | 8 nm |
| Die Size | 628 mm² | 628 mm² |
| Transistor Count | 28 billion | 28 billion |
| Transistor Density | 44.59 MTr/mm² | 44.59 MTr/mm² |
| Memory Type | GDDR6X | GDDR6X |
| Memory Size | 12 GB | 24 GB |
| Memory Clock | 1188 MHz | 1219 MHz |
| Effective Memory Speed | 19000 Mbps | 19500 Mbps |
| ECC | No | No |
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 8.6 | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 2 | DLSS 2 |