Quick/Comparisons
32 | Gaming | 11 |
39 | Workstation | 15 |
33 | AI/ML |
Compare with something else?
Compare GeForce RTX 2070 with another →15 |
27 | Energy Efficiency | 89 |
34 | Quick Comparison Final Score | 25 |
| TU104 | Graphics Processor | Arrow Lake iGPU |
| 2560 | Cores | 896 |
| 160 / 64 | TMUs / ROPs | 56 / 28 |
| 2361.66 | Blender GPU | 640.3 |
| 77 | Forza Horizon 5 | 25 |
| 109 | The Witcher 3 | 31 |
| 150 | Counter-Strike 2 | 25 |
| 91 | Far Cry 6 | 32 |
| 61 | Hogwarts Legacy | 12 |
| 82 | Call of Duty | 28 |
| 58 | Ghost of Tsushima | 15 |
| 71 | Cyberpunk 2077 | 18 |
| 113 | Tomb Raider | 31 |
| 90 | Average FPS | 24 |
| 111 | 1080p High | 32 |
| 90 | 1080p Ultra | 24 |
| 66 | 1440p Ultra | 18 |
| 38 | 4K Ultra | - |
| Low | Margin of Error | Low |
| 105349 | GB6 Compute Score | 36282 |
| 166.7 img/sec | Background Blur | 70.9 img/sec |
| 103.3 img/sec | Face Detection | 34.9 img/sec |
| 4.21 Gpixels/sec | Horizon Detection | 1.13 Gpixels/sec |
| 5.56 Gpixels/sec | Edge Detection | 1.42 Gpixels/sec |
| 5.58 Gpixels/sec | Gaussian Blur | 1.96 Gpixels/sec |
| 1.17 Gpixels/sec | Feature Matching | 0.45 Gpixels/sec |
| 489.7 Gpixels/sec | Stereo Matching | 131.5 Gpixels/sec |
| 13242.9 FPS | Particle Physics | 7360.9 FPS |
| OpenCL | API | OpenCL |
| 18141 | G3D Mark Score | 6157 |
| 878 | G2D Mark | 793 |
| 153 FPS | DirectX 11 | 43 FPS |
| 67 FPS | DirectX 12 | 27 FPS |
| 7473 Ops/s | GPU Compute | 2702 Ops/s |
| 16276 | GB6 ML Single Precision | 7262 |
| 27406 | GB6 ML Half Precision | 9964 |
| 10983 | GB6 ML Quantized | 5008 |
| 6648 | Image Classification (SP) | 3978 |
| 16442 | Image Segmentation (HP) | 8374 |
| 15383 | Image Super Resolution (Q) | 5792 |
| 32861 | Face Detection (HP) | 13023 |
| 66348 | Pose Estimation (Q) | 16149 |
| 2166 | Text Classification (SP) | 1356 |
| 4239 | Machine Translation (HP) | 2594 |
| 8194 | Object Detection (SP) | 4754 |
| 26192 | Depth Estimation (Q) | 12040 |
| 137642 | Style Transfer (SP) | 51653 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 113 GPixel/s | Pixel Fill Rate | 62 GPixel/s |
| 283 GTexel/s | Texture Fill Rate | 123 GTexel/s |
| 9.1 TFLOPS | FLOPS (FP32) | 3.9 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 x8 |
| 215 W | TGP | 35 W |
| TSMC | Manufacturing | TSMC |
| 12 nm | Fabrication Process | 5 nm |
| 545 mm² | Die Size | — |
| 13 billion | Transistor Count | — |
| 23.85 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| 7.5 | CUDA | No |
| Yes | Ray Tracing | Yes |
| DLSS 2 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| July 9, 2019 | Released | January 6, 2025 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Generic |
| Mid-range | Segment | Entry-level |
| Turing | Architecture | Xe+ |
| TU104 | GPU Codename | Arrow Lake iGPU |
| -Intel Core i7 9700Kor above | Recommended CPU | -Intel Core Ultra 5 225Hor above |
| 10053 | Steel Nomad Lite Score | 2921 |
| 10167 | Time Spy | 3407 |
| 45871 | Solar Bay | 12731 |
| 6032 | Port Royal | 1902 |
| 25675 | Fire Strike | 8020 |
| 20745 | Wild Life Extreme | 5985 |
| 102728 | Night Raid | 37233 |
| 1605 MHz | Base Clock | 300 MHz |
| 1770 MHz | Boost Clock | 2200 MHz |
| 2560 | Shading Units | 896 |
| 160 | Texture Mapping Units (TMUs) | 56 |
| 64 | Render Output Units (ROPs) | 28 |
| 40 | Compute Units (Pipelines) | 7 |
| 320 | Tensor Cores | 112 |
| 40 | Ray-tracing Cores | 7 |
| 64KB per cluster | L1 Cache | — |
| 4MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |