Quick/Comparisons
The GeForce RTX 5070 Ti takes the lead in gaming performance, outscoring the GeForce RTX 2080 SUPER by 39 points. Its superior performance is largely due to its higher benchmark scores.
The GeForce RTX 2080 SUPER edges out the GeForce RTX 5070 Ti in workstation performance, with a 32-point lead. This is likely due to its higher workstation hallmark score.
The GeForce RTX 5070 Ti outperforms the GeForce RTX 2080 SUPER in AI/ML tasks, with a 34-point difference. This is likely due to its higher AI/ML hallmark score.
37 | Gaming | 76 |
42 | Workstation | 74 |
32 | AI/ML | 66 |
27 | Energy Efficiency | 49 |
38 | Quick Comparison Final Score | 74 |
| TU104 | Graphics Processor | GB203-200-A1 |
| 3072 | Cores | 8960 |
| 192 / 64 | TMUs / ROPs | 280 / 96 |
| 2407.76 | Blender GPU | 7584.67 |
| 86 | Forza Horizon 5 | 166 |
| 121 | The Witcher 3 | 213 |
| 169 | Counter-Strike 2 | 219 |
| 105 | Far Cry 6 | 159 |
| 68 | Hogwarts Legacy | 135 |
| 97 | Call of Duty | 205 |
| 64 | Ghost of Tsushima | 121 |
| 82 | Cyberpunk 2077 | 174 |
| 131 | Tomb Raider | 260 |
| 103 | Average FPS | 184 |
| 124 | 1080p High | 217 |
| 103 | 1080p Ultra | 184 |
| 75 | 1440p Ultra | 148 |
| 42 | 4K Ultra | 86 |
| Low | Margin of Error | Low |
| 122905 | GB6 Compute Score | 240508 |
| 197.1 img/sec | Background Blur | 297.9 img/sec |
| 110.7 img/sec | Face Detection | 218.6 img/sec |
| 5.03 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 6.5 Gpixels/sec | Edge Detection | 13.9 Gpixels/sec |
| 7.05 Gpixels/sec | Gaussian Blur | 14.8 Gpixels/sec |
| 1.28 Gpixels/sec | Feature Matching | 2.03 Gpixels/sec |
| 576.8 Gpixels/sec | Stereo Matching | 1290 Gpixels/sec |
| 15732.9 FPS | Particle Physics | 35438.3 FPS |
| OpenCL | API | OpenCL |
| 19452 | G3D Mark Score | 32425 |
| 919 | G2D Mark | 1329 |
| 167 FPS | DirectX 11 | 304 FPS |
| 75 FPS | DirectX 12 | 126 FPS |
| 8204 Ops/s | GPU Compute | 18089 Ops/s |
| 16090 | GB6 ML Single Precision | 36504 |
| 26121 | GB6 ML Half Precision | 64459 |
| 10870 | GB6 ML Quantized | 27312 |
| 6780 | Image Classification (SP) | 14913 |
| 15029 | Image Segmentation (HP) | 45199 |
| 15410 | Image Super Resolution (Q) | 39360 |
| 30849 | Face Detection (HP) | 84188 |
| 71857 | Pose Estimation (Q) | 161400 |
| 1983 | Text Classification (SP) | 4010 |
| 3417 | Machine Translation (HP) | 7973 |
| 8214 | Object Detection (SP) | 18934 |
| 26815 | Depth Estimation (Q) | 67761 |
| 148497 | Style Transfer (SP) | 335879 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 116 GPixel/s | Pixel Fill Rate | 235 GPixel/s |
| 348 GTexel/s | Texture Fill Rate | 687 GTexel/s |
| 11.2 TFLOPS | FLOPS (FP32) | 43.9 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 8 GB | Memory Size | 16 GB |
| 1937 MHz | Memory Clock | 1750 MHz |
| 15500 Mbps | Effective Memory Speed | 28000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 495.9 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 250 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 545 mm² | Die Size | 378 mm² |
| 13 billion | Transistor Count | 45.6 billion |
| 23.85 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 |
| 7.5 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| July 23, 2019 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Turing | Architecture | Blackwell 2.0 |
| TU104 | GPU Codename | GB203-200-A1 |
| -Intel Core i9 9900Kor above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 11569 | Steel Nomad Lite Score | 29989 |
| 11621 | Time Spy | 27815 |
| 52083 | Solar Bay | 136964 |
| 7001 | Port Royal | 19613 |
| 28788 | Fire Strike | 67382 |
| 23792 | Wild Life Extreme | 57734 |
| 108111 | Night Raid | 189734 |
| 1650 MHz | Base Clock | 2295 MHz |
| 1815 MHz | Boost Clock | 2452 MHz |
| 3072 | Shading Units | 8960 |
| 192 | Texture Mapping Units (TMUs) | 280 |
| 64 | Render Output Units (ROPs) | 96 |
| 48 | Compute Units (Pipelines) | 70 |
| 384 | Tensor Cores | 280 |
| 48 | Ray-tracing Cores | 70 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 2080 with another →