Quick/Comparisons
The GeForce RTX 5070 Ti takes the lead in gaming performance with a score of 76, outpacing the GeForce RTX 3080 Ti's 60. This is largely due to the 5070 Ti's superior architecture and increased memory capacity.
The GeForce RTX 5070 Ti edges out the GeForce RTX 3080 Ti in content creation with a score of 74, thanks to its more efficient architecture and larger memory pool.
The GeForce RTX 5070 Ti leads in AI and machine learning with a score of 66, outperforming the GeForce RTX 3080 Ti's 46. This is due to the 5070 Ti's improved architecture and increased memory capacity.
60 | Gaming | 76 |
64 | Workstation | 74 |
46 | AI/ML | 66 |
35 | Energy Efficiency | 49 |
59 | Quick Comparison Final Score | 74 |
| GA102 | Graphics Processor | GB203-200-A1 |
| 10240 | Cores | 8960 |
| 320 / 112 | TMUs / ROPs | 280 / 96 |
| 5565.9 | Blender GPU | 7584.67 |
| 128 | Forza Horizon 5 | 166 |
| 174 | The Witcher 3 | 213 |
| 205 | Counter-Strike 2 | 219 |
| 139 | Far Cry 6 | 159 |
| 108 | Hogwarts Legacy | 135 |
| 161 | Call of Duty | 205 |
| 96 | Ghost of Tsushima | 121 |
| 128 | Cyberpunk 2077 | 174 |
| 219 | Tomb Raider | 260 |
| 151 | Average FPS | 184 |
| 180 | 1080p High | 217 |
| 151 | 1080p Ultra | 184 |
| 117 | 1440p Ultra | 148 |
| 69 | 4K Ultra | 86 |
| Low | Margin of Error | Low |
| 196756 | GB6 Compute Score | 240508 |
| 239.8 img/sec | Background Blur | 297.9 img/sec |
| 156.8 img/sec | Face Detection | 218.6 img/sec |
| 10.8 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 14.8 Gpixels/sec | Edge Detection | 13.9 Gpixels/sec |
| 11.9 Gpixels/sec | Gaussian Blur | 14.8 Gpixels/sec |
| 1.53 Gpixels/sec | Feature Matching | 2.03 Gpixels/sec |
| 889.6 Gpixels/sec | Stereo Matching | 1290 Gpixels/sec |
| 26054.6 FPS | Particle Physics | 35438.3 FPS |
| OpenCL | API | OpenCL |
| 26777 | G3D Mark Score | 32425 |
| 1095 | G2D Mark | 1329 |
| 222 FPS | DirectX 11 | 304 FPS |
| 109 FPS | DirectX 12 | 126 FPS |
| 15025 Ops/s | GPU Compute | 18089 Ops/s |
| 25945 | GB6 ML Single Precision | 36504 |
| 38430 | GB6 ML Half Precision | 64459 |
| 15331 | GB6 ML Quantized | 27312 |
| 9747 | Image Classification (SP) | 14913 |
| 26654 | Image Segmentation (HP) | 45199 |
| 21475 | Image Super Resolution (Q) | 39360 |
| 49813 | Face Detection (HP) | 84188 |
| 135370 | Pose Estimation (Q) | 161400 |
| 2796 | Text Classification (SP) | 4010 |
| 4757 | Machine Translation (HP) | 7973 |
| 12924 | Object Detection (SP) | 18934 |
| 36756 | Depth Estimation (Q) | 67761 |
| 274032 | Style Transfer (SP) | 335879 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 186 GPixel/s | Pixel Fill Rate | 235 GPixel/s |
| 533 GTexel/s | Texture Fill Rate | 687 GTexel/s |
| 34.1 TFLOPS | FLOPS (FP32) | 43.9 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 12 GB | Memory Size | 16 GB |
| 1188 MHz | Memory Clock | 1750 MHz |
| 19000 Mbps | Effective Memory Speed | 28000 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | No |
| 912 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 350 W | TGP | 300 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 628 mm² | Die Size | 378 mm² |
| 28 billion | Transistor Count | 45.6 billion |
| 44.59 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.6 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 3, 2021 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Ampere | Architecture | Blackwell 2.0 |
| GA102 | GPU Codename | GB203-200-A1 |
| -Intel Core i9 12900Kor above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 21408 | Steel Nomad Lite Score | 29989 |
| 19632 | Time Spy | 27815 |
| 96597 | Solar Bay | 136964 |
| 13265 | Port Royal | 19613 |
| 47867 | Fire Strike | 67382 |
| 42716 | Wild Life Extreme | 57734 |
| 144955 | Night Raid | 189734 |
| 1365 MHz | Base Clock | 2295 MHz |
| 1665 MHz | Boost Clock | 2452 MHz |
| 10240 | Shading Units | 8960 |
| 320 | Texture Mapping Units (TMUs) | 280 |
| 112 | Render Output Units (ROPs) | 96 |
| 80 | Compute Units (Pipelines) | 70 |
| 320 | Tensor Cores | 280 |
| 80 | Ray-tracing Cores | 70 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 6MB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 3080 with another →