Quick/Comparisons
5 | Gaming | 11 |
9 | Workstation | 15 |
3 | AI/ML |
Compare with something else?
Compare GeForce MX250 with another →15 |
68 | Energy Efficiency | 89 |
16 | Quick Comparison Final Score | 25 |
| GP108 | Graphics Processor | Arrow Lake iGPU |
| 384 | Cores | 896 |
| 24 / 16 | TMUs / ROPs | 56 / 28 |
| 87.25 | Blender GPU | 640.3 |
| - | Forza Horizon 5 | 25 |
| - | The Witcher 3 | 31 |
| 17 | Counter-Strike 2 | 25 |
| 16 | Far Cry 6 | 32 |
| - | Hogwarts Legacy | 12 |
| 23 | Call of Duty | 28 |
| - | Ghost of Tsushima | 15 |
| — | Cyberpunk 2077 | 18 |
| - | Tomb Raider | 31 |
| 10 | Average FPS | 24 |
| 14 | 1080p High | 32 |
| 10 | 1080p Ultra | 24 |
| - | 1440p Ultra | 18 |
| - | 4K Ultra | - |
| Medium | Margin of Error | Low |
| 10870 | GB6 Compute Score | 36282 |
| 27.8 img/sec | Background Blur | 70.9 img/sec |
| 13 img/sec | Face Detection | 34.9 img/sec |
| 0.4 Gpixels/sec | Horizon Detection | 1.13 Gpixels/sec |
| 0.59 Gpixels/sec | Edge Detection | 1.42 Gpixels/sec |
| 0.64 Gpixels/sec | Gaussian Blur | 1.96 Gpixels/sec |
| 0.12 Gpixels/sec | Feature Matching | 0.45 Gpixels/sec |
| 34 Gpixels/sec | Stereo Matching | 131.5 Gpixels/sec |
| 960.9 FPS | Particle Physics | 7360.9 FPS |
| OpenCL | API | OpenCL |
| 2376 | G3D Mark Score | 6157 |
| 238 | G2D Mark | 793 |
| 18 FPS | DirectX 11 | 43 FPS |
| 12 FPS | DirectX 12 | 27 FPS |
| 1011 Ops/s | GPU Compute | 2702 Ops/s |
| 1840 | GB6 ML Single Precision | 7262 |
| 1885 | GB6 ML Half Precision | 9964 |
| 1401 | GB6 ML Quantized | 5008 |
| 405 | Image Classification (SP) | 3978 |
| 968 | Image Segmentation (HP) | 8374 |
| 2273 | Image Super Resolution (Q) | 5792 |
| 1652 | Face Detection (HP) | 13023 |
| 8039 | Pose Estimation (Q) | 16149 |
| 837 | Text Classification (SP) | 1356 |
| 944 | Machine Translation (HP) | 2594 |
| 552 | Object Detection (SP) | 4754 |
| 3111 | Depth Estimation (Q) | 12040 |
| 17477 | Style Transfer (SP) | 51653 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 25 GPixel/s | Pixel Fill Rate | 62 GPixel/s |
| 38 GTexel/s | Texture Fill Rate | 123 GTexel/s |
| 1.2 TFLOPS | FLOPS (FP32) | 3.9 TFLOPS |
| GDDR5 | Memory Type | System Shared |
| 2 GB | Memory Size | — |
| 1502 MHz | Memory Clock | — |
| 6000 Mbps | Effective Memory Speed | — |
| 64-bit | Bus | — |
| — | ECC | — |
| 48 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x4 | Interface | PCIe 4.0 x8 |
| 25 W | TGP | 35 W |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 5 nm |
| 74 mm² | Die Size | — |
| 1.8 billion | Transistor Count | — |
| 24.32 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.2 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 6.1 | CUDA | No |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4 | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| February 21, 2009 | Released | January 6, 2025 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| Entry-level | Segment | Entry-level |
| Pascal | Architecture | Xe+ |
| GP108 | GPU Codename | Arrow Lake iGPU |
| -Intel Core i7 1065G7or above | Recommended CPU | -Intel Core Ultra 5 225Hor above |
| 896 | Steel Nomad Lite Score | 2921 |
| 1078 | Time Spy | 3407 |
| — | Solar Bay | 12731 |
| — | Port Royal | 1902 |
| 3619 | Fire Strike | 8020 |
| 2227 | Wild Life Extreme | 5985 |
| 14485 | Night Raid | 37233 |
| 1519 MHz | Base Clock | 300 MHz |
| 1582 MHz | Boost Clock | 2200 MHz |
| 384 | Shading Units | 896 |
| 24 | Texture Mapping Units (TMUs) | 56 |
| 16 | Render Output Units (ROPs) | 28 |
| 3 | Compute Units (Pipelines) | 7 |
| No | Tensor Cores | 112 |
| No | Ray-tracing Cores | 7 |
| 48KB per cluster | L1 Cache | — |
| 512KB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |