Quick/Comparisons
The GeForce RTX 5080's superior gaming performance is evident, with a 50-point gap in this category. Its Blackwell 2.0 architecture and 16GB GDDR7 memory contribute to its dominance.
The GeForce RTX 5080 takes the lead in content creation, thanks to its strong workstation performance and 16GB GDDR7 memory. This provides a significant advantage over the Radeon RX 6700 XT's 12GB GDDR6 memory.
The GeForce RTX 5080's capable AI/ML compute capabilities and 16GB GDDR7 memory give it a 34-point lead in this category. This makes it the clear winner for AI and machine learning tasks.
87 | Gaming | 37 |
85 | Workstation | 41 |
70 | AI/ML | 36 |
49 | Energy Efficiency | 37 |
84 | Quick Comparison Final Score | 38 |
| GB203-400 | Graphics Processor | Navi 22 |
| 10752 | Cores | 2560 |
| 336 / 112 | TMUs / ROPs | 160 / 64 |
| 9138.54 | Blender GPU | 1512.89 |
| 185 | Forza Horizon 5 | 91 |
| 237 | The Witcher 3 | 120 |
| 237 | Counter-Strike 2 | 154 |
| 176 | Far Cry 6 | 107 |
| 154 | Hogwarts Legacy | 73 |
| 241 | Call of Duty | 112 |
| 137 | Ghost of Tsushima | 72 |
| 190 | Cyberpunk 2077 | 80 |
| 270 | Tomb Raider | 133 |
| 203 | Average FPS | 105 |
| 239 | 1080p High | 131 |
| 203 | 1080p Ultra | 105 |
| 164 | 1440p Ultra | 76 |
| 97 | 4K Ultra | 43 |
| Low | Margin of Error | Low |
| 297747 | GB6 Compute Score | 110742 |
| 319.6 img/sec | Background Blur | 245.8 img/sec |
| 225 img/sec | Face Detection | 153.3 img/sec |
| 13.6 Gpixels/sec | Horizon Detection | 3.99 Gpixels/sec |
| 19.5 Gpixels/sec | Edge Detection | 5.82 Gpixels/sec |
| 20.4 Gpixels/sec | Gaussian Blur | 4.37 Gpixels/sec |
| 2.33 Gpixels/sec | Feature Matching | 1.01 Gpixels/sec |
| 1750 Gpixels/sec | Stereo Matching | 474.4 Gpixels/sec |
| 43676.6 FPS | Particle Physics | 13872.6 FPS |
| OpenCL | API | OpenCL |
| 35695 | G3D Mark Score | 19733 |
| 1407 | G2D Mark | 954 |
| 327 FPS | DirectX 11 | 173 FPS |
| 144 FPS | DirectX 12 | 77 FPS |
| 19397 Ops/s | GPU Compute | 9261 Ops/s |
| 38994 | GB6 ML Single Precision | 21026 |
| 66609 | GB6 ML Half Precision | 21983 |
| 29206 | GB6 ML Quantized | 16106 |
| 15441 | Image Classification (SP) | 9076 |
| 47173 | Image Segmentation (HP) | 10972 |
| 43223 | Image Super Resolution (Q) | 24228 |
| 92863 | Face Detection (HP) | 32365 |
| 202202 | Pose Estimation (Q) | 100249 |
| 3701 | Text Classification (SP) | 2204 |
| 7905 | Machine Translation (HP) | 4803 |
| 20955 | Object Detection (SP) | 9882 |
| 69068 | Depth Estimation (Q) | 37762 |
| 349205 | Style Transfer (SP) | 210688 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 293 GPixel/s | Pixel Fill Rate | 165 GPixel/s |
| 879 GTexel/s | Texture Fill Rate | 413 GTexel/s |
| 56.3 TFLOPS | FLOPS (FP32) | 13.2 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 16 GB | Memory Size | 12 GB |
| 1875 MHz | Memory Clock | 2000 MHz |
| 30000 Mbps | Effective Memory Speed | 16000 Mbps |
| 256-bit | Bus | 192-bit |
| No | ECC | No |
| 960 GB/s | Memory Bandwidth | 384 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 360 W | TGP | 230 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 7 nm |
| 378 mm² | Die Size | 335 mm² |
| 45.6 billion | Transistor Count | 17 billion |
| 120.63 MTr/mm² | Transistor Density | 50.75 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 12 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| January 7, 2025 | Released | March 3, 2021 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | RDNA 2.0 |
| GB203-400 | GPU Codename | Navi 22 |
| -Intel Core Ultra 7 265Kor above | Recommended CPU | -Intel Core i5 12600Kor above |
| 36200 | Steel Nomad Lite Score | 11424 |
| 32989 | Time Spy | 12816 |
| 160901 | Solar Bay | 50234 |
| 23257 | Port Royal | 6199 |
| 75518 | Fire Strike | 35840 |
| 69544 | Wild Life Extreme | 22926 |
| 200077 | Night Raid | 130460 |
| 2295 MHz | Base Clock | 2321 MHz |
| 2617 MHz | Boost Clock | 2581 MHz |
| 10752 | Shading Units | 2560 |
| 336 | Texture Mapping Units (TMUs) | 160 |
| 112 | Render Output Units (ROPs) | 64 |
| 84 | Compute Units (Pipelines) | — |
| 336 | Tensor Cores | — |
| 84 | Ray-tracing Cores | 40 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 64MB shared | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5080 with another →