Quick/Comparisons
37 | Gaming | 66 |
59 | Workstation | 79 |
45 | AI/ML |
Compare with something else?
Compare Nvidia RTX Pro with another →62 |
59 | Energy Efficiency | 49 |
47 | Quick Comparison Final Score | 66 |
| GB205-300-A1 | Graphics Processor | GB202-300-A1 |
| 5888 | Cores | 10496 |
| 184 / 80 | TMUs / ROPs | 328 / 112 |
| 3405.25 | Blender GPU | 7401.59 |
| 79 | Forza Horizon 5 | 135 |
| 111 | The Witcher 3 | 180 |
| 149 | Counter-Strike 2 | 214 |
| 94 | Far Cry 6 | 148 |
| 63 | Hogwarts Legacy | 114 |
| 83 | Call of Duty | 175 |
| 58 | Ghost of Tsushima | 106 |
| 73 | Cyberpunk 2077 | 145 |
| 112 | Tomb Raider | 245 |
| 91 | Average FPS | 162 |
| 112 | 1080p High | 191 |
| 91 | 1080p Ultra | 162 |
| 66 | 1440p Ultra | 127 |
| 37 | 4K Ultra | 75 |
| High | Margin of Error | High |
| 167869 | GB6 Compute Score | 246458 |
| 238.8 img/sec | Background Blur | 267.1 img/sec |
| 147.6 img/sec | Face Detection | 183.2 img/sec |
| 6.73 Gpixels/sec | Horizon Detection | 11.5 Gpixels/sec |
| 9.27 Gpixels/sec | Edge Detection | 15.8 Gpixels/sec |
| 10.7 Gpixels/sec | Gaussian Blur | 18.1 Gpixels/sec |
| 1.68 Gpixels/sec | Feature Matching | 2.01 Gpixels/sec |
| 778.4 Gpixels/sec | Stereo Matching | 1330 Gpixels/sec |
| 23023.5 FPS | Particle Physics | 35463.8 FPS |
| OpenCL | API | OpenCL |
| 21959 | G3D Mark Score | 24043 |
| 833 | G2D Mark | 843 |
| 224 FPS | DirectX 11 | 254 FPS |
| 100 FPS | DirectX 12 | 109 FPS |
| 7578 Ops/s | GPU Compute | 8247 Ops/s |
| 24473 | GB6 ML Single Precision | 31330 |
| 44496 | GB6 ML Half Precision | 53746 |
| 18924 | GB6 ML Quantized | 24267 |
| 9790 | Image Classification (SP) | 12454 |
| 28672 | Image Segmentation (HP) | 33371 |
| 26553 | Image Super Resolution (Q) | 35476 |
| 53161 | Face Detection (HP) | 67998 |
| 120306 | Pose Estimation (Q) | 168369 |
| 3406 | Text Classification (SP) | 3491 |
| 5910 | Machine Translation (HP) | 6115 |
| 12573 | Object Detection (SP) | 16115 |
| 47957 | Depth Estimation (Q) | 59893 |
| 199379 | Style Transfer (SP) | 279891 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 128-194 GPixel/s | Pixel Fill Rate | 188-202 GPixel/s |
| 295-447 GTexel/s | Texture Fill Rate | 551-593 GTexel/s |
| 18.9-28.6 TFLOPS | FLOPS (FP32) | 35.3-37.9 TFLOPS |
| GDDR7 | Memory Type | GDDR7 |
| 12 GB | Memory Size | 24 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 28000 Mbps | Effective Memory Speed | 28000 Mbps |
| 192-bit | Bus | 256-bit |
| No | ECC | — |
| 672 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 5.0 x16 |
| 60-140 W (configurable) | TGP | 95-175 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 263 mm² | Die Size | 378 mm² |
| 31.1 billion | Transistor Count | 45.6 billion |
| 118.25 MTr/mm² | Transistor Density | 120.63 MTr/mm² |
| 12.2 | DirectX | 12.2 |
| 1.4 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 4 |
| 2.1b | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| March 18, 2025 | Released | March 18, 2025 |
| Laptop | Case | Laptop |
| Professional | Purpose | Professional |
| Mid-range | Segment | High-end |
| Blackwell 2.0 | Architecture | Blackwell 2.0 |
| GB205-300-A1 | GPU Codename | GB202-300-A1 |
| -Intel Core Ultra 7 265HXor above | Recommended CPU | -Intel Core Ultra 9 275HXor above |
| 8100 | Steel Nomad Lite Score | 24118 |
| 12327 | Time Spy | 21548 |
| 69295 | Solar Bay | 96355 |
| — | Port Royal | 14090 |
| 28339 | Fire Strike | 47636 |
| — | Wild Life Extreme | — |
| — | Night Raid | — |
| 848-1605 MHz (configurable) | Base Clock | 990-1680 MHz (configurable) |
| 1605-2430 MHz (configurable) | Boost Clock | 1680-1807 MHz (configurable) |
| 5888 | Shading Units | 10496 |
| 184 | Texture Mapping Units (TMUs) | 328 |
| 80 | Render Output Units (ROPs) | 112 |
| 46 | Compute Units (Pipelines) | 82 |
| 184 | Tensor Cores | 328 |
| 46 | Ray-tracing Cores | 82 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 48MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |