Quick/Comparisons
The Nvidia RTX 6000 Ada dominates in gaming performance with an 80 score, significantly outpacing the GeForce RTX 2070 Mobile's 25 score.
The Nvidia RTX 6000 Ada excels in workstation performance with a 94 score, leaving the GeForce RTX 2070 Mobile's 35 score far behind.
The Nvidia RTX 6000 Ada's 75 score in AI/ML compute surpasses the GeForce RTX 2070 Mobile's 24 score, although the gap is relatively small.
25 | Gaming | 80 |
35 | Workstation | 94 |
24 | AI/ML | 75 |
46 | Energy Efficiency | 44 |
31 | Quick Comparison Final Score | 83 |
| TU106B | Graphics Processor | AD102 |
| 2304 | Cores | 18176 |
| 144 / 64 | TMUs / ROPs | 568 / 192 |
| 1823.68 | Blender GPU | 11038.91 |
| 61 | Forza Horizon 5 | 165 |
| 84 | The Witcher 3 | 219 |
| 117 | Counter-Strike 2 | 221 |
| 74 | Far Cry 6 | 164 |
| 45 | Hogwarts Legacy | 133 |
| 61 | Call of Duty | 216 |
| 42 | Ghost of Tsushima | 123 |
| 53 | Cyberpunk 2077 | 172 |
| 84 | Tomb Raider | 267 |
| 69 | Average FPS | 187 |
| 87 | 1080p High | 219 |
| 69 | 1080p Ultra | 187 |
| 49 | 1440p Ultra | 148 |
| 26 | 4K Ultra | 89 |
| Low | Margin of Error | High |
| 92843 | GB6 Compute Score | 389848 |
| 159 img/sec | Background Blur | 618.3 img/sec |
| 91.2 img/sec | Face Detection | 399.9 img/sec |
| 3.67 Gpixels/sec | Horizon Detection | 15.1 Gpixels/sec |
| 5.1 Gpixels/sec | Edge Detection | 22.1 Gpixels/sec |
| 5.03 Gpixels/sec | Gaussian Blur | 26.3 Gpixels/sec |
| 1.08 Gpixels/sec | Feature Matching | 2.33 Gpixels/sec |
| 411.9 Gpixels/sec | Stereo Matching | 2210 Gpixels/sec |
| 10180.5 FPS | Particle Physics | 53494.5 FPS |
| OpenCL | API | OpenCL |
| 12357 | G3D Mark Score | 28613 |
| 602 | G2D Mark | 1005 |
| 111 FPS | DirectX 11 | 284 FPS |
| 41 FPS | DirectX 12 | 102 FPS |
| 4490 Ops/s | GPU Compute | 22439 Ops/s |
| 10388 | GB6 ML Single Precision | 37270 |
| 17021 | GB6 ML Half Precision | 53469 |
| 7357 | GB6 ML Quantized | 27850 |
| 3954 | Image Classification (SP) | 13367 |
| 9425 | Image Segmentation (HP) | 32477 |
| 11209 | Image Super Resolution (Q) | 42056 |
| 18147 | Face Detection (HP) | 69004 |
| 47333 | Pose Estimation (Q) | 230965 |
| 1546 | Text Classification (SP) | 3491 |
| 2209 | Machine Translation (HP) | 5545 |
| 4976 | Object Detection (SP) | 18668 |
| 18466 | Depth Estimation (Q) | 68370 |
| 90152 | Style Transfer (SP) | 520389 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 92-95 GPixel/s | Pixel Fill Rate | 481 GPixel/s |
| 207-214 GTexel/s | Texture Fill Rate | 1423 GTexel/s |
| 6.6-6.8 TFLOPS | FLOPS (FP32) | 91.1 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 48 GB |
| 1750 MHz | Memory Clock | 2500 MHz |
| 14000 Mbps | Effective Memory Speed | 20000 Mbps |
| 256-bit | Bus | 384-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x16 |
| 115 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 5 nm |
| 445 mm² | Die Size | 609 mm² |
| 10.8 billion | Transistor Count | 76 billion |
| 24.27 MTr/mm² | Transistor Density | 124.79 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 7.5 | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 3 |
| 1.4 | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 29, 2019 | Released | December 3, 2022 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Professional |
| High-end | Segment | High-end |
| Turing | Architecture | Ada Lovelace |
| TU106B | GPU Codename | AD102 |
| -Intel Core i7 10750Hor above | Recommended CPU | -Intel Core i9 14900Kor above |
| 7234 | Steel Nomad Lite Score | 32284 |
| 7566 | Time Spy | 26686 |
| 31700 | Solar Bay | 145429 |
| 4446 | Port Royal | 19557 |
| 19887 | Fire Strike | 62803 |
| 14527 | Wild Life Extreme | 53640 |
| 65976 | Night Raid | 148225 |
| 1215-1305 MHz (configurable) | Base Clock | 915 MHz |
| 1440-1485 MHz (configurable) | Boost Clock | 2505 MHz |
| 2304 | Shading Units | 18176 |
| 144 | Texture Mapping Units (TMUs) | 568 |
| 64 | Render Output Units (ROPs) | 192 |
| 36 | Compute Units (Pipelines) | 142 |
| 288 | Tensor Cores | 568 |
| 36 | Ray-tracing Cores | 142 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 96MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare GeForce RTX 2070 with another →