Quick/Comparisons
The GeForce RTX 5080 takes the lead in gaming performance, thanks to its higher score of 87 compared to the GeForce RTX 4070 Ti SUPER's 70.
The GeForce RTX 5080 edges out the GeForce RTX 4070 Ti SUPER in content creation, with a score of 85 compared to 72.
The GeForce RTX 5080 has a slight advantage in AI/ML compute, with a score of 70 compared to the GeForce RTX 4070 Ti SUPER's 59.
70 | Gaming | 87 |
72 | Workstation | 85 |
59 | AI/ML | 70 |
46 | Energy Efficiency | 49 |
69 | Quick Comparison Final Score | 84 |
| AD103 | Graphics Processor | GB203-400 |
| 8448 | Cores | 10752 |
| 264 / 96 | TMUs / ROPs | 336 / 112 |
| 7089.35 | Blender GPU | 9138.54 |
| 150 | Forza Horizon 5 | 185 |
| 198 | The Witcher 3 | 237 |
| 220 | Counter-Strike 2 | 237 |
| 152 | Far Cry 6 | 176 |
| 118 | Hogwarts Legacy | 154 |
| 188 | Call of Duty | 241 |
| 111 | Ghost of Tsushima | 137 |
| 155 | Cyberpunk 2077 | 190 |
| 249 | Tomb Raider | 270 |
| 171 | Average FPS | 203 |
| 200 | 1080p High | 239 |
| 171 | 1080p Ultra | 203 |
| 134 | 1440p Ultra | 164 |
| 79 | 4K Ultra | 97 |
| Low | Margin of Error | Low |
| 237068 | GB6 Compute Score | 297747 |
| 331.7 img/sec | Background Blur | 319.6 img/sec |
| 211.6 img/sec | Face Detection | 225 img/sec |
| 9.63 Gpixels/sec | Horizon Detection | 13.6 Gpixels/sec |
| 13.7 Gpixels/sec | Edge Detection | 19.5 Gpixels/sec |
| 13.9 Gpixels/sec | Gaussian Blur | 20.4 Gpixels/sec |
| 2.15 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 1210 Gpixels/sec | Stereo Matching | 1750 Gpixels/sec |
| 33566 FPS | Particle Physics | 43676.6 FPS |
| OpenCL | API | OpenCL |
| 31798 | G3D Mark Score | 35695 |
| 1240 | G2D Mark | 1407 |
| 277 FPS | DirectX 11 | 327 FPS |
| 119 FPS | DirectX 12 | 144 FPS |
| 18264 Ops/s | GPU Compute | 19397 Ops/s |
| 32793 | GB6 ML Single Precision | 38994 |
| 47412 | GB6 ML Half Precision | 66609 |
| 24566 | GB6 ML Quantized | 29206 |
| 12970 | Image Classification (SP) | 15441 |
| 26364 | Image Segmentation (HP) | 47173 |
| 37217 | Image Super Resolution (Q) | 43223 |
| 58720 | Face Detection (HP) | 92863 |
| 177604 | Pose Estimation (Q) | 202202 |
| 3815 | Text Classification (SP) | 3701 |
| 5829 | Machine Translation (HP) | 7905 |
| 15675 | Object Detection (SP) | 20955 |
| 62447 | Depth Estimation (Q) | 69068 |
| 357918 | Style Transfer (SP) | 349205 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 251 GPixel/s | Pixel Fill Rate | 293 GPixel/s |
| 689 GTexel/s | Texture Fill Rate | 879 GTexel/s |
| 44.1 TFLOPS | FLOPS (FP32) | 56.3 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 16 GB | Memory Size | 16 GB |
| 1313 MHz | Memory Clock | 1875 MHz |
| 21000 Mbps | Effective Memory Speed | 30000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 672.3 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 285 W | TGP | 360 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| 379 mm² | Die Size | 378 mm² |
| 45 billion | Transistor Count | 45.6 billion |
| 118.73 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 |
| 8.9 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | DLSS 4 |
| 1.4a | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 24, 2024 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Blackwell 2.0 |
| AD103 | GPU Codename | GB203-400 |
| -Intel Core i7 14700Kor above | Recommended CPU | -Intel Core Ultra 7 265Kor above |
| 25741 | Steel Nomad Lite Score | 36200 |
| 24222 | Time Spy | 32989 |
| 116542 | Solar Bay | 160901 |
| 15802 | Port Royal | 23257 |
| 56340 | Fire Strike | 75518 |
| 49901 | Wild Life Extreme | 69544 |
| 176609 | Night Raid | 200077 |
| 2340 MHz | Base Clock | 2295 MHz |
| 2610 MHz | Boost Clock | 2617 MHz |
| 8448 | Shading Units | 10752 |
| 264 | Texture Mapping Units (TMUs) | 336 |
| 96 | Render Output Units (ROPs) | 112 |
| 66 | Compute Units (Pipelines) | 84 |
| 264 | Tensor Cores | 336 |
| 66 | Ray-tracing Cores | 84 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 4070 with another →