Quick/Comparisons
The Nvidia RTX 6000 Ada takes the lead in gaming performance with an impressive 80 score, thanks to its exceptional Ada Lovelace architecture and 48GB GDDR6 memory.
The Nvidia RTX 6000 Ada dominates content creation with a 94 score, driven by its strong workstation performance and capable AI/ML compute capabilities.
The Nvidia RTX 6000 Ada leads in AI/ML with a 75 score, leveraging its capable AI tensor cores and efficient Ada Lovelace architecture.
80 | Gaming | 31 |
94 | Workstation | 52 |
75 | AI/ML | 31 |
44 | Energy Efficiency | 48 |
83 | Quick Comparison Final Score | 40 |
| AD102 | Graphics Processor | GA104 |
| 18176 | Cores | 5888 |
| 568 / 192 | TMUs / ROPs | 184 / 96 |
| 11038.91 | Blender GPU | 2757.5 |
| 165 | Forza Horizon 5 | 71 |
| 219 | The Witcher 3 | 100 |
| 221 | Counter-Strike 2 | 137 |
| 164 | Far Cry 6 | 86 |
| 133 | Hogwarts Legacy | 56 |
| 216 | Call of Duty | 75 |
| 123 | Ghost of Tsushima | 52 |
| 172 | Cyberpunk 2077 | 66 |
| 267 | Tomb Raider | 100 |
| 187 | Average FPS | 83 |
| 219 | 1080p High | 104 |
| 187 | 1080p Ultra | 83 |
| 148 | 1440p Ultra | 60 |
| 89 | 4K Ultra | 34 |
| High | Margin of Error | High |
| 389848 | GB6 Compute Score | 119474 |
| 618.3 img/sec | Background Blur | 158.7 img/sec |
| 399.9 img/sec | Face Detection | 115.8 img/sec |
| 15.1 Gpixels/sec | Horizon Detection | 5.95 Gpixels/sec |
| 22.1 Gpixels/sec | Edge Detection | 8.2 Gpixels/sec |
| 26.3 Gpixels/sec | Gaussian Blur | 5.85 Gpixels/sec |
| 2.33 Gpixels/sec | Feature Matching | 1.13 Gpixels/sec |
| 2210 Gpixels/sec | Stereo Matching | 505.2 Gpixels/sec |
| 53494.5 FPS | Particle Physics | 15517.5 FPS |
| OpenCL | API | OpenCL |
| 28613 | G3D Mark Score | 16804 |
| 1005 | G2D Mark | 714 |
| 284 FPS | DirectX 11 | 131 FPS |
| 102 FPS | DirectX 12 | 77 FPS |
| 22439 Ops/s | GPU Compute | 6679 Ops/s |
| 37270 | GB6 ML Single Precision | 14763 |
| 53469 | GB6 ML Half Precision | 23628 |
| 27850 | GB6 ML Quantized | 10163 |
| 13367 | Image Classification (SP) | 6159 |
| 32477 | Image Segmentation (HP) | 12031 |
| 42056 | Image Super Resolution (Q) | 15490 |
| 69004 | Face Detection (HP) | 29614 |
| 230965 | Pose Estimation (Q) | 65582 |
| 3491 | Text Classification (SP) | 1918 |
| 5545 | Machine Translation (HP) | 3097 |
| 18668 | Object Detection (SP) | 8192 |
| 68370 | Depth Estimation (Q) | 23635 |
| 520389 | Style Transfer (SP) | 142647 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 481 GPixel/s | Pixel Fill Rate | 99-143 GPixel/s |
| 1423 GTexel/s | Texture Fill Rate | 190-273 GTexel/s |
| 91.1 TFLOPS | FLOPS (FP32) | 12.2-17.5 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 48 GB | Memory Size | 16 GB |
| 2500 MHz | Memory Clock | 2000 MHz |
| 20000 Mbps | Effective Memory Speed | 16000 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | Yes |
| 960 GB/s | Memory Bandwidth | 512 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 300 W | TGP | 80-140 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 5 nm | Fabrication Process | 8 nm |
| 609 mm² | Die Size | 392 mm² |
| 76 billion | Transistor Count | 17.4 billion |
| 124.79 MTr/mm² | Transistor Density | 44.39 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 8.9 | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | — |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| December 3, 2022 | Released | March 22, 2022 |
| Desktop | Case | Laptop |
| Professional | Purpose | Professional |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | Ampere |
| AD102 | GPU Codename | GA104 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core i7 12800HXor above |
| 32284 | Steel Nomad Lite Score | 8802 |
| 26686 | Time Spy | 9410 |
| 145429 | Solar Bay | 39802 |
| 19557 | Port Royal | 6116 |
| 62803 | Fire Strike | 25494 |
| 53640 | Wild Life Extreme | 19741 |
| 148225 | Night Raid | 93933 |
| 915 MHz | Base Clock | 510-1035 MHz (configurable) |
| 2505 MHz | Boost Clock | 1035-1485 MHz (configurable) |
| 18176 | Shading Units | 5888 |
| 568 | Texture Mapping Units (TMUs) | 184 |
| 192 | Render Output Units (ROPs) | 96 |
| 142 | Compute Units (Pipelines) | 46 |
| 568 | Tensor Cores | 184 |
| 142 | Ray-tracing Cores | 46 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 96MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare Nvidia RTX 6000 with another →