Quick/Comparisons
25 | Gaming | 45 |
35 | Workstation | 45 |
24 | AI/ML |
Compare with something else?
Compare GeForce RTX 2070 with another →39 |
46 | Energy Efficiency | 65 |
31 | Quick Comparison Final Score | 48 |
| TU106B | Graphics Processor | GB206-300 |
| 2304 | Cores | 4608 |
| 144 / 64 | TMUs / ROPs | 144 / 48 |
| 1823.68 | Blender GPU | 4007.35 |
| 61 | Forza Horizon 5 | 96 |
| 84 | The Witcher 3 | 137 |
| 117 | Counter-Strike 2 | 195 |
| 74 | Far Cry 6 | 116 |
| 45 | Hogwarts Legacy | 79 |
| 61 | Call of Duty | 110 |
| 42 | Ghost of Tsushima | 73 |
| 53 | Cyberpunk 2077 | 92 |
| 84 | Tomb Raider | 149 |
| 69 | Average FPS | 116 |
| 87 | 1080p High | 140 |
| 69 | 1080p Ultra | 116 |
| 49 | 1440p Ultra | 88 |
| 26 | 4K Ultra | 51 |
| Low | Margin of Error | Low |
| 92843 | GB6 Compute Score | 134209 |
| 159 img/sec | Background Blur | 213.4 img/sec |
| 91.2 img/sec | Face Detection | 130.4 img/sec |
| 3.67 Gpixels/sec | Horizon Detection | 4.89 Gpixels/sec |
| 5.1 Gpixels/sec | Edge Detection | 6.23 Gpixels/sec |
| 5.03 Gpixels/sec | Gaussian Blur | 7.41 Gpixels/sec |
| 1.08 Gpixels/sec | Feature Matching | 1.46 Gpixels/sec |
| 411.9 Gpixels/sec | Stereo Matching | 661.9 Gpixels/sec |
| 10180.5 FPS | Particle Physics | 19395.6 FPS |
| OpenCL | API | OpenCL |
| 12357 | G3D Mark Score | 19173 |
| 602 | G2D Mark | 884 |
| 111 FPS | DirectX 11 | 186 FPS |
| 41 FPS | DirectX 12 | 91 FPS |
| 4490 Ops/s | GPU Compute | 7114 Ops/s |
| 10388 | GB6 ML Single Precision | 22022 |
| 17021 | GB6 ML Half Precision | 40929 |
| 7357 | GB6 ML Quantized | 17069 |
| 3954 | Image Classification (SP) | 8984 |
| 9425 | Image Segmentation (HP) | 26270 |
| 11209 | Image Super Resolution (Q) | 24606 |
| 18147 | Face Detection (HP) | 48283 |
| 47333 | Pose Estimation (Q) | 98180 |
| 1546 | Text Classification (SP) | 3260 |
| 2209 | Machine Translation (HP) | 5770 |
| 4976 | Object Detection (SP) | 11172 |
| 18466 | Depth Estimation (Q) | 43305 |
| 90152 | Style Transfer (SP) | 165555 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 92-95 GPixel/s | Pixel Fill Rate | 68-121 GPixel/s |
| 207-214 GTexel/s | Texture Fill Rate | 203-363 GTexel/s |
| 6.6-6.8 TFLOPS | FLOPS (FP32) | 13-23.2 TFLOPS |
| GDDR6 | Memory Type | GDDR7 |
| 8 GB | Memory Size | 8 GB |
| 1750 MHz | Memory Clock | 1750 MHz |
| 14000 Mbps | Effective Memory Speed | 24000 Mbps |
| 256-bit | Bus | 128-bit |
| No | ECC | No |
| 448 GB/s | Memory Bandwidth | 384 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 5.0 x16 |
| 115 W | TGP | 50-125 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 4 nm |
| 445 mm² | Die Size | 181 mm² |
| 10.8 billion | Transistor Count | 21.9 billion |
| 24.27 MTr/mm² | Transistor Density | 120.99 MTr/mm² |
| 12 | DirectX | 12.2 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 7.5 | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | DLSS 4 |
| 1.4 | DisplayPort | 2.1b |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 29, 2019 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Turing | Architecture | Blackwell 2.0 |
| TU106B | GPU Codename | GB206-300 |
| -Intel Core i7 10750Hor above | Recommended CPU | -Intel Core Ultra 7 255HXor above |
| 7234 | Steel Nomad Lite Score | 13896 |
| 7566 | Time Spy | 13563 |
| 31700 | Solar Bay | 59662 |
| 4446 | Port Royal | 8648 |
| 19887 | Fire Strike | 35860 |
| 14527 | Wild Life Extreme | 24526 |
| 65976 | Night Raid | 125756 |
| 1215-1305 MHz (configurable) | Base Clock | 890-1410 MHz (configurable) |
| 1440-1485 MHz (configurable) | Boost Clock | 1410-2520 MHz (configurable) |
| 2304 | Shading Units | 4608 |
| 144 | Texture Mapping Units (TMUs) | 144 |
| 64 | Render Output Units (ROPs) | 48 |
| 36 | Compute Units (Pipelines) | 36 |
| 288 | Tensor Cores | 144 |
| 36 | Ray-tracing Cores | 36 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |