Quick/Comparisons
The Nvidia RTX 6000 Ada takes the lead in gaming performance with its 80 score, thanks to its exceptional Ada Lovelace architecture and 48GB GDDR6 memory.
The Nvidia RTX 6000 Ada excels in content creation with its 94 score, driven by its strong workstation performance and capable AI/ML compute capabilities.
The Nvidia RTX 6000 Ada leads in AI/ML performance with its 75 score, leveraging its capable AI/ML compute and 48GB GDDR6 memory for efficient processing.
80 | Gaming | 66 |
94 | Workstation | 79 |
75 | AI/ML | 62 |
44 | Energy Efficiency | 49 |
83 | Quick Comparison Final Score | 66 |
| AD102 | Graphics Processor | GB202-300-A1 |
| 18176 | Cores | 10496 |
| 568 / 192 | TMUs / ROPs | 328 / 112 |
| 11038.91 | Blender GPU | 7401.59 |
| 165 | Forza Horizon 5 | 135 |
| 219 | The Witcher 3 | 180 |
| 221 | Counter-Strike 2 | 214 |
| 164 | Far Cry 6 | 148 |
| 133 | Hogwarts Legacy | 114 |
| 216 | Call of Duty | 175 |
| 123 | Ghost of Tsushima | 106 |
| 172 | Cyberpunk 2077 | 145 |
| 267 | Tomb Raider | 245 |
| 187 | Average FPS | 162 |
| 219 | 1080p High | 191 |
| 187 | 1080p Ultra | 162 |
| 148 | 1440p Ultra | 127 |
| 89 | 4K Ultra | 75 |
| High | Margin of Error | High |
| 389848 | GB6 Compute Score | 246458 |
| 618.3 img/sec | Background Blur | 267.1 img/sec |
| 399.9 img/sec | Face Detection | 183.2 img/sec |
| 15.1 Gpixels/sec | Horizon Detection | 11.5 Gpixels/sec |
| 22.1 Gpixels/sec | Edge Detection | 15.8 Gpixels/sec |
| 26.3 Gpixels/sec | Gaussian Blur | 18.1 Gpixels/sec |
| 2.33 Gpixels/sec | Feature Matching | 2.01 Gpixels/sec |
| 2210 Gpixels/sec | Stereo Matching | 1330 Gpixels/sec |
| 53494.5 FPS | Particle Physics | 35463.8 FPS |
| OpenCL | API | OpenCL |
| 28613 | G3D Mark Score | 24043 |
| 1005 | G2D Mark | 843 |
| 284 FPS | DirectX 11 | 254 FPS |
| 102 FPS | DirectX 12 | 109 FPS |
| 22439 Ops/s | GPU Compute | 8247 Ops/s |
| 37270 | GB6 ML Single Precision | 31330 |
| 53469 | GB6 ML Half Precision | 53746 |
| 27850 | GB6 ML Quantized | 24267 |
| 13367 | Image Classification (SP) | 12454 |
| 32477 | Image Segmentation (HP) | 33371 |
| 42056 | Image Super Resolution (Q) | 35476 |
| 69004 | Face Detection (HP) | 67998 |
| 230965 | Pose Estimation (Q) | 168369 |
| 3491 | Text Classification (SP) | 3491 |
| 5545 | Machine Translation (HP) | 6115 |
| 18668 | Object Detection (SP) | 16115 |
| 68370 | Depth Estimation (Q) | 59893 |
| 520389 | Style Transfer (SP) | 279891 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 481 GPixel/s | Pixel Fill Rate | 188-202 GPixel/s |
| 1423 GTexel/s | Texture Fill Rate | 551-593 GTexel/s |
| 91.1 TFLOPS | FLOPS (FP32) | 35.3-37.9 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 48 GB | Memory Size | 24 GB |
| 2500 MHz | Memory Clock | 1750 MHz |
| 20000 Mbps | Effective Memory Speed | 28000 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | — |
| 960 GB/s | Memory Bandwidth | 896 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 5.0 x16 |
| 300 W | TGP | 95-175 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 609 mm² | Die Size | 378 mm² |
| 76 billion | Transistor Count | 45.6 billion |
| 124.79 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 |
| December 3, 2022 | Released | March 18, 2025 |
| Desktop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Blackwell 2.0 |
| AD102 | GPU Codename | GB202-300-A1 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core Ultra 9 275HXor above |
| 32284 | Steel Nomad Lite Score | 24118 |
| 26686 | Time Spy | 21548 |
| 145429 | Solar Bay | 96355 |
| 19557 | Port Royal | 14090 |
| 62803 | Fire Strike | 47636 |
| 53640 | Wild Life Extreme | — |
| 148225 | Night Raid | — |
| 915 MHz | Base Clock | 990-1680 MHz (configurable) |
| 2505 MHz | Boost Clock | 1680-1807 MHz (configurable) |
| 18176 | Shading Units | 10496 |
| 568 | Texture Mapping Units (TMUs) | 328 |
| 192 | Render Output Units (ROPs) | 112 |
| 142 | Compute Units (Pipelines) | 82 |
| 568 | Tensor Cores | 328 |
| 142 | Ray-tracing Cores | 82 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 96MB shared | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare Nvidia RTX 6000 with another →