Quick/Comparisons
The GeForce RTX 5080 takes the lead in gaming performance, thanks to its higher score of 87, outpacing the GeForce RTX 3070 Ti's score of 46.
The GeForce RTX 5080's strong workstation performance earns it the win in content creation, with a score of 85, compared to the GeForce RTX 3070 Ti's score of 49.
The GeForce RTX 5080's capable AI/ML compute capabilities give it the edge in AI & Machine Learning, with a score of 70, outperforming the GeForce RTX 3070 Ti's score of 39.
46 | Gaming | 87 |
49 | Workstation | 85 |
39 | AI/ML | 70 |
35 | Energy Efficiency | 49 |
46 | Quick Comparison Final Score | 84 |
| GA104 | Graphics Processor | GB203-400 |
| 6144 | Cores | 10752 |
| 192 / 96 | TMUs / ROPs | 336 / 112 |
| 3746.83 | Blender GPU | 9138.54 |
| 104 | Forza Horizon 5 | 185 |
| 143 | The Witcher 3 | 237 |
| 198 | Counter-Strike 2 | 237 |
| 125 | Far Cry 6 | 176 |
| 85 | Hogwarts Legacy | 154 |
| 120 | Call of Duty | 241 |
| 81 | Ghost of Tsushima | 137 |
| 102 | Cyberpunk 2077 | 190 |
| 161 | Tomb Raider | 270 |
| 124 | Average FPS | 203 |
| 150 | 1080p High | 239 |
| 124 | 1080p Ultra | 203 |
| 93 | 1440p Ultra | 164 |
| 54 | 4K Ultra | 97 |
| Low | Margin of Error | Low |
| 136096 | GB6 Compute Score | 297747 |
| 197 img/sec | Background Blur | 319.6 img/sec |
| 128.1 img/sec | Face Detection | 225 img/sec |
| 6.56 Gpixels/sec | Horizon Detection | 13.6 Gpixels/sec |
| 8.81 Gpixels/sec | Edge Detection | 19.5 Gpixels/sec |
| 6.47 Gpixels/sec | Gaussian Blur | 20.4 Gpixels/sec |
| 1.26 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 609.3 Gpixels/sec | Stereo Matching | 1750 Gpixels/sec |
| 18205 FPS | Particle Physics | 43676.6 FPS |
| OpenCL | API | OpenCL |
| 23260 | G3D Mark Score | 35695 |
| 1061 | G2D Mark | 1407 |
| 192 FPS | DirectX 11 | 327 FPS |
| 91 FPS | DirectX 12 | 144 FPS |
| 11452 Ops/s | GPU Compute | 19397 Ops/s |
| 22516 | GB6 ML Single Precision | 38994 |
| 36377 | GB6 ML Half Precision | 66609 |
| 14215 | GB6 ML Quantized | 29206 |
| 8615 | Image Classification (SP) | 15441 |
| 24659 | Image Segmentation (HP) | 47173 |
| 20631 | Image Super Resolution (Q) | 43223 |
| 43834 | Face Detection (HP) | 92863 |
| 98347 | Pose Estimation (Q) | 202202 |
| 3162 | Text Classification (SP) | 3701 |
| 4911 | Machine Translation (HP) | 7905 |
| 11498 | Object Detection (SP) | 20955 |
| 34719 | Depth Estimation (Q) | 69068 |
| 196833 | Style Transfer (SP) | 349205 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 170 GPixel/s | Pixel Fill Rate | 293 GPixel/s |
| 340 GTexel/s | Texture Fill Rate | 879 GTexel/s |
| 21.7 TFLOPS | FLOPS (FP32) | 56.3 TFLOPS |
| GDDR6X | Memory Type | GDDR7 |
| 8 GB | Memory Size | 16 GB |
| 1188 MHz | Memory Clock | 1875 MHz |
| 19000 Mbps | Effective Memory Speed | 30000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 608.3 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 290 W | TGP | 360 W |
| Samsung | Manufacturing | TSMC |
| 8 nm | Fabrication Process | 4 nm |
| 392 mm² | Die Size | 378 mm² |
| 17 billion | Transistor Count | 45.6 billion |
| 43.37 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 |
| June 10, 2021 | Released | January 7, 2025 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Ampere | Architecture | Blackwell 2.0 |
| GA104 | GPU Codename | GB203-400 |
| -Intel Core i7 12700Kor above | Recommended CPU | -Intel Core Ultra 7 265Kor above |
| 15402 | Steel Nomad Lite Score | 36200 |
| 14880 | Time Spy | 32989 |
| 69900 | Solar Bay | 160901 |
| 8884 | Port Royal | 23257 |
| 37238 | Fire Strike | 75518 |
| 31911 | Wild Life Extreme | 69544 |
| 134012 | Night Raid | 200077 |
| 1575 MHz | Base Clock | 2295 MHz |
| 1770 MHz | Boost Clock | 2617 MHz |
| 6144 | Shading Units | 10752 |
| 192 | Texture Mapping Units (TMUs) | 336 |
| 96 | Render Output Units (ROPs) | 112 |
| 48 | Compute Units (Pipelines) | 84 |
| 192 | Tensor Cores | 336 |
| 48 | Ray-tracing Cores | 84 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 3070 with another →