Quick/Comparisons
The Nvidia RTX 6000 Ada dominates in gaming with an 80 score, thanks to its excellent performance in popular titles.
The Nvidia RTX 6000 Ada excels in content creation with a 94 score, offering strong workstation performance and capable AI/ML compute.
The Nvidia RTX 6000 Ada leads in AI/ML with a 75 score, thanks to its capable AI/ML compute and dedicated tensor cores.
80 | Gaming | 28 |
94 | Workstation | 35 |
75 | AI/ML | 26 |
44 | Energy Efficiency | 36 |
83 | Quick Comparison Final Score | 30 |
| AD102 | Graphics Processor | Navi 10 |
| 18176 | Cores | 2560 |
| 568 / 192 | TMUs / ROPs | 160 / 64 |
| 11038.91 | Blender GPU | 978.14 |
| 165 | Forza Horizon 5 | 73 |
| 219 | The Witcher 3 | 93 |
| 221 | Counter-Strike 2 | 126 |
| 164 | Far Cry 6 | 90 |
| 133 | Hogwarts Legacy | 57 |
| 216 | Call of Duty | 85 |
| 123 | Ghost of Tsushima | 58 |
| 172 | Cyberpunk 2077 | 60 |
| 267 | Tomb Raider | 107 |
| 187 | Average FPS | 83 |
| 219 | 1080p High | 106 |
| 187 | 1080p Ultra | 83 |
| 148 | 1440p Ultra | 58 |
| 89 | 4K Ultra | 31 |
| High | Margin of Error | Low |
| 389848 | GB6 Compute Score | 81739 |
| 618.3 img/sec | Background Blur | 148 img/sec |
| 399.9 img/sec | Face Detection | 89.5 img/sec |
| 15.1 Gpixels/sec | Horizon Detection | 3.52 Gpixels/sec |
| 22.1 Gpixels/sec | Edge Detection | 4.98 Gpixels/sec |
| 26.3 Gpixels/sec | Gaussian Blur | 4.11 Gpixels/sec |
| 2.33 Gpixels/sec | Feature Matching | 0.75 Gpixels/sec |
| 2210 Gpixels/sec | Stereo Matching | 295.8 Gpixels/sec |
| 53494.5 FPS | Particle Physics | 10480.7 FPS |
| OpenCL | API | OpenCL |
| 28613 | G3D Mark Score | 16097 |
| 1005 | G2D Mark | 922 |
| 284 FPS | DirectX 11 | 115 FPS |
| 102 FPS | DirectX 12 | 64 FPS |
| 22439 Ops/s | GPU Compute | 7555 Ops/s |
| 37270 | GB6 ML Single Precision | 14920 |
| 53469 | GB6 ML Half Precision | 16852 |
| 27850 | GB6 ML Quantized | 11883 |
| 13367 | Image Classification (SP) | 6764 |
| 32477 | Image Segmentation (HP) | 7615 |
| 42056 | Image Super Resolution (Q) | 19081 |
| 69004 | Face Detection (HP) | 20621 |
| 230965 | Pose Estimation (Q) | 73667 |
| 3491 | Text Classification (SP) | 1970 |
| 5545 | Machine Translation (HP) | 2417 |
| 18668 | Object Detection (SP) | 6684 |
| 68370 | Depth Estimation (Q) | 30456 |
| 520389 | Style Transfer (SP) | 147087 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 481 GPixel/s | Pixel Fill Rate | 122 GPixel/s |
| 1423 GTexel/s | Texture Fill Rate | 305 GTexel/s |
| 91.1 TFLOPS | FLOPS (FP32) | 9.8 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 48 GB | Memory Size | 8 GB |
| 2500 MHz | Memory Clock | 1750 MHz |
| 20000 Mbps | Effective Memory Speed | 14000 Mbps |
| 384-bit | Bus | 256-bit |
| No | ECC | No |
| 960 GB/s | Memory Bandwidth | 448 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 300 W | TGP | 225 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 7 nm |
| 609 mm² | Die Size | 251 mm² |
| 76 billion | Transistor Count | 10 billion |
| 124.79 MTr/mm² | Transistor Density | 39.84 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | No |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| December 3, 2022 | Released | July 7, 2019 |
| Desktop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 1.0 |
| AD102 | GPU Codename | Navi 10 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core i5 9600Kor above |
| 32284 | Steel Nomad Lite Score | 8570 |
| 26686 | Time Spy | 9422 |
| 145429 | Solar Bay | — |
| 19557 | Port Royal | — |
| 62803 | Fire Strike | 27547 |
| 53640 | Wild Life Extreme | 18391 |
| 148225 | Night Raid | 103065 |
| 915 MHz | Base Clock | 1605 MHz |
| 2505 MHz | Boost Clock | 1905 MHz |
| 18176 | Shading Units | 2560 |
| 568 | Texture Mapping Units (TMUs) | 160 |
| 192 | Render Output Units (ROPs) | 64 |
| 142 | Compute Units (Pipelines) | — |
| 568 | Tensor Cores | No |
| 142 | Ray-tracing Cores | No |
| 128KB per cluster | L1 Cache | — |
| 96MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare Nvidia RTX 6000 with another →