Quick/Comparisons
25 | Gaming | 6 |
35 | Workstation | 9 |
24 | AI/ML |
Compare with something else?
Compare GeForce RTX 2070 with another →9 |
46 | Energy Efficiency | 86 |
31 | Quick Comparison Final Score | 20 |
| TU106B | Graphics Processor | Krackan Point |
| 2304 | Cores | 256 |
| 144 / 64 | TMUs / ROPs | 16 / 8 |
| 1823.68 | Blender GPU | 122.02 |
| 61 | Forza Horizon 5 | 13 |
| 84 | The Witcher 3 | 12 |
| 117 | Counter-Strike 2 | 18 |
| 74 | Far Cry 6 | 16 |
| 45 | Hogwarts Legacy | - |
| 61 | Call of Duty | 19 |
| 42 | Ghost of Tsushima | 9 |
| 53 | Cyberpunk 2077 | 9 |
| 84 | Tomb Raider | 17 |
| 69 | Average FPS | 13 |
| 87 | 1080p High | 18 |
| 69 | 1080p Ultra | 13 |
| 49 | 1440p Ultra | 10 |
| 26 | 4K Ultra | - |
| Low | Margin of Error | High |
| 92843 | GB6 Compute Score | 14025 |
| 159 img/sec | Background Blur | 31.8 img/sec |
| 91.2 img/sec | Face Detection | 16.8 img/sec |
| 3.67 Gpixels/sec | Horizon Detection | 0.46 Gpixels/sec |
| 5.1 Gpixels/sec | Edge Detection | 0.58 Gpixels/sec |
| 5.03 Gpixels/sec | Gaussian Blur | 0.42 Gpixels/sec |
| 1.08 Gpixels/sec | Feature Matching | 0.18 Gpixels/sec |
| 411.9 Gpixels/sec | Stereo Matching | 52.5 Gpixels/sec |
| 10180.5 FPS | Particle Physics | 2048.6 FPS |
| OpenCL | API | OpenCL |
| 12357 | G3D Mark Score | — |
| 602 | G2D Mark | — |
| 111 FPS | DirectX 11 | — |
| 41 FPS | DirectX 12 | — |
| 4490 Ops/s | GPU Compute | — |
| 10388 | GB6 ML Single Precision | 4884 |
| 17021 | GB6 ML Half Precision | 6067 |
| 7357 | GB6 ML Quantized | 3946 |
| 3954 | Image Classification (SP) | 1988 |
| 9425 | Image Segmentation (HP) | 2184 |
| 11209 | Image Super Resolution (Q) | 4788 |
| 18147 | Face Detection (HP) | 6857 |
| 47333 | Pose Estimation (Q) | 17396 |
| 1546 | Text Classification (SP) | 1628 |
| 2209 | Machine Translation (HP) | 2053 |
| 4976 | Object Detection (SP) | 1825 |
| 18466 | Depth Estimation (Q) | 8471 |
| 90152 | Style Transfer (SP) | 31032 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 92-95 GPixel/s | Pixel Fill Rate | 23 GPixel/s |
| 207-214 GTexel/s | Texture Fill Rate | 46 GTexel/s |
| 6.6-6.8 TFLOPS | FLOPS (FP32) | 1.5 TFLOPS |
| GDDR6 | Memory Type | System Shared |
| 8 GB | Memory Size | — |
| 1750 MHz | Memory Clock | — |
| 14000 Mbps | Effective Memory Speed | — |
| 256-bit | Bus | — |
| No | ECC | — |
| 448 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x16 |
| 115 W | TGP | 15-54 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 445 mm² | Die Size | — |
| 10.8 billion | Transistor Count | — |
| 24.27 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 2.1 |
| 7.5 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4 | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| January 29, 2019 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| High-end | Segment | Entry-level |
| Turing | Architecture | RDNA 3.5 |
| TU106B | GPU Codename | Krackan Point |
| -Intel Core i7 10750Hor above | Recommended CPU | -AMD Ryzen AI 5 340or above |
| 7234 | Steel Nomad Lite Score | 1293 |
| 7566 | Time Spy | 1700 |
| 31700 | Solar Bay | 7155 |
| 4446 | Port Royal | 577 |
| 19887 | Fire Strike | 5317 |
| 14527 | Wild Life Extreme | — |
| 65976 | Night Raid | 22727 |
| 1215-1305 MHz (configurable) | Base Clock | 400 MHz |
| 1440-1485 MHz (configurable) | Boost Clock | 2900 MHz |
| 2304 | Shading Units | 256 |
| 144 | Texture Mapping Units (TMUs) | 16 |
| 64 | Render Output Units (ROPs) | 8 |
| 36 | Compute Units (Pipelines) | 4 |
| 288 | Tensor Cores | No |
| 36 | Ray-tracing Cores | 4 |
| 64KB per cluster | L1 Cache | 512KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |