Quick/Comparisons
The Nvidia RTX 6000 Ada's superior gaming performance makes it the clear winner, with a 41-point gap in this use case.
The Nvidia RTX 6000 Ada's strong workstation performance and high score of 94 make it the clear winner in this use case.
The Nvidia RTX 6000 Ada's capable AI/ML compute and higher score of 75 make it the winner in this use case, despite a relatively close gap.
68 | Energy Efficiency | 44 |
44 | Quick Comparison Final Score | 83 |
39 | Gaming | 80 |
41 | Workstation | 94 |
34 | AI/ML | 75 |
| GB206 | Graphics Processor | AD102 |
| 3328 | Cores | 18176 |
| 104 / 48 | TMUs / ROPs | 568 / 192 |
| 3486.18 | Blender GPU | 11038.91 |
| 88 | Forza Horizon 5 | 165 |
| 124 | The Witcher 3 | 219 |
| 169 | Counter-Strike 2 | 221 |
| 104 | Far Cry 6 | 164 |
| 73 | Hogwarts Legacy | 133 |
| 102 | Call of Duty | 216 |
| 66 | Ghost of Tsushima | 123 |
| 83 | Cyberpunk 2077 | 172 |
| 131 | Tomb Raider | 267 |
| 104 | Average FPS | 187 |
| 127 | 1080p High | 219 |
| 104 | 1080p Ultra | 187 |
| 77 | 1440p Ultra | 148 |
| 44 | 4K Ultra | 89 |
| Low | Margin of Error | High |
| 116707 | GB6 Compute Score | 389848 |
| 190.8 img/sec | Background Blur | 618.3 img/sec |
| 115.9 img/sec | Face Detection | 399.9 img/sec |
| 4.17 Gpixels/sec | Horizon Detection | 15.1 Gpixels/sec |
| 5.28 Gpixels/sec | Edge Detection | 22.1 Gpixels/sec |
| 7.1 Gpixels/sec | Gaussian Blur | 26.3 Gpixels/sec |
| 1.32 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 523.3 Gpixels/sec | Stereo Matching | 2210 Gpixels/sec |
| 16169.3 FPS | Particle Physics | 53494.5 FPS |
| OpenCL | API | OpenCL |
| 16865 | G3D Mark Score | 28613 |
| 854 | G2D Mark | 1005 |
| 163 FPS | DirectX 11 | 284 FPS |
| 79 FPS | DirectX 12 | 102 FPS |
| 6246 Ops/s | GPU Compute | 22439 Ops/s |
| 18679 | GB6 ML Single Precision | 37270 |
| 35323 | GB6 ML Half Precision | 53469 |
| 14707 | GB6 ML Quantized | 27850 |
| 7525 | Image Classification (SP) | 13367 |
| 23623 | Image Segmentation (HP) | 32477 |
| 19973 | Image Super Resolution (Q) | 42056 |
| 41164 | Face Detection (HP) | 69004 |
| 77589 | Pose Estimation (Q) | 230965 |
| 2880 | Text Classification (SP) | 3491 |
| 5811 | Machine Translation (HP) | 5545 |
| 9966 | Object Detection (SP) | 18668 |
| 37206 | Depth Estimation (Q) | 68370 |
| 136961 | Style Transfer (SP) | 520389 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 70-120 GPixel/s | Pixel Fill Rate | 481 GPixel/s |
| 151-260 GTexel/s | Texture Fill Rate | 1423 GTexel/s |
| 9.7-16.6 TFLOPS | FLOPS (FP32) | 91.1 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 48 GB |
| 1750 MHz | Memory Clock | 2500 MHz |
| 24000 Mbps | Effective Memory Speed | 20000 Mbps |
| 128-bit | Bus | 384-bit |
| No | ECC | No |
| 384 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 45-115 W (configurable) | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| 181 mm² | Die Size | 609 mm² |
| 21.9 billion | Transistor Count | 76 billion |
| 120.99 MTr/mm² | Transistor Density | 124.79 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 12 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | DLSS 3 |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| April 14, 2025 | Released | December 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | High-end |
| Blackwell 2.0 | Architecture | Ada Lovelace |
| GB206 | GPU Codename | AD102 |
| -Intel Core Ultra 5 245HXor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 11858 | Steel Nomad Lite Score | 32284 |
| 12013 | Time Spy | 26686 |
| 52525 | Solar Bay | 145429 |
| 7419 | Port Royal | 19557 |
| 31691 | Fire Strike | 62803 |
| 21567 | Wild Life Extreme | 53640 |
| 116013 | Night Raid | 148225 |
| 952-1455 MHz (configurable) | Base Clock | 915 MHz |
| 1455-2497 MHz (configurable) | Boost Clock | 2505 MHz |
| 3328 | Shading Units | 18176 |
| 104 | Texture Mapping Units (TMUs) | 568 |
| 48 | Render Output Units (ROPs) | 192 |
| 26 | Compute Units (Pipelines) | 142 |
| 104 | Tensor Cores | 568 |
| 26 | Ray-tracing Cores | 142 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 32MB shared | L2 Cache | 96MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 5060 with another →