Quick/Comparisons
5 | Gaming | 35 |
9 | Workstation | 41 |
3 | AI/ML |
Compare with something else?
Compare GeForce MX250 with another →34 |
68 | Energy Efficiency | 27 |
16 | Quick Comparison Final Score | 37 |
| GP108 | Graphics Processor | TU104 |
| 384 | Cores | 2944 |
| 24 / 16 | TMUs / ROPs | 184 / 64 |
| 87.25 | Blender GPU | 2335.41 |
| - | Forza Horizon 5 | 81 |
| - | The Witcher 3 | 120 |
| 17 | Counter-Strike 2 | 160 |
| 16 | Far Cry 6 | 99 |
| - | Hogwarts Legacy | 65 |
| 23 | Call of Duty | 93 |
| - | Ghost of Tsushima | 62 |
| — | Cyberpunk 2077 | 75 |
| - | Tomb Raider | 123 |
| 10 | Average FPS | 98 |
| 14 | 1080p High | 119 |
| 10 | 1080p Ultra | 98 |
| - | 1440p Ultra | 72 |
| - | 4K Ultra | 40 |
| Medium | Margin of Error | Low |
| 10870 | GB6 Compute Score | 118637 |
| 27.8 img/sec | Background Blur | 191.8 img/sec |
| 13 img/sec | Face Detection | 115.9 img/sec |
| 0.4 Gpixels/sec | Horizon Detection | 4.74 Gpixels/sec |
| 0.59 Gpixels/sec | Edge Detection | 6.2 Gpixels/sec |
| 0.64 Gpixels/sec | Gaussian Blur | 6.56 Gpixels/sec |
| 0.12 Gpixels/sec | Feature Matching | 1.3 Gpixels/sec |
| 34 Gpixels/sec | Stereo Matching | 499.7 Gpixels/sec |
| 960.9 FPS | Particle Physics | 15858.8 FPS |
| OpenCL | API | OpenCL |
| 2376 | G3D Mark Score | 18607 |
| 238 | G2D Mark | 900 |
| 18 FPS | DirectX 11 | 159 FPS |
| 12 FPS | DirectX 12 | 71 FPS |
| 1011 Ops/s | GPU Compute | 7761 Ops/s |
| 1840 | GB6 ML Single Precision | 17223 |
| 1885 | GB6 ML Half Precision | 28694 |
| 1401 | GB6 ML Quantized | 11608 |
| 405 | Image Classification (SP) | 7122 |
| 968 | Image Segmentation (HP) | 17897 |
| 2273 | Image Super Resolution (Q) | 16120 |
| 1652 | Face Detection (HP) | 34245 |
| 8039 | Pose Estimation (Q) | 69601 |
| 837 | Text Classification (SP) | 2181 |
| 944 | Machine Translation (HP) | 4328 |
| 552 | Object Detection (SP) | 8748 |
| 3111 | Depth Estimation (Q) | 28373 |
| 17477 | Style Transfer (SP) | 154510 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 25 GPixel/s | Pixel Fill Rate | 109 GPixel/s |
| 38 GTexel/s | Texture Fill Rate | 315 GTexel/s |
| 1.2 TFLOPS | FLOPS (FP32) | 10.1 TFLOPS |
| GDDR5 | Memory Type | GDDR6 |
| 2 GB | Memory Size | 8 GB |
| 1502 MHz | Memory Clock | 1750 MHz |
| 6000 Mbps | Effective Memory Speed | 14000 Mbps |
| 64-bit | Bus | 256-bit |
| — | ECC | No |
| 48 GB/s | Memory Bandwidth | 448 GB/s |
| PCIe 3.0 x4 | Interface | PCIe 3.0 x16 |
| 25 W | TGP | 215 W |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 12 nm |
| 74 mm² | Die Size | 545 mm² |
| 1.8 billion | Transistor Count | 13 billion |
| 24.32 MTr/mm² | Transistor Density | 23.85 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 6.1 | CUDA | 7.5 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 1.4 | DisplayPort | 1.4a |
| Nvidia | Vendor | Nvidia |
| Discrete | Build | Discrete |
| February 21, 2009 | Released | September 20, 2018 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | High-end |
| Pascal | Architecture | Turing |
| GP108 | GPU Codename | TU104 |
| -Intel Core i7 1065G7or above | Recommended CPU | -AMD Ryzen 9 9900Xor above |
| 896 | Steel Nomad Lite Score | 10886 |
| 1078 | Time Spy | 11079 |
| — | Solar Bay | 49857 |
| — | Port Royal | 6459 |
| 3619 | Fire Strike | 27671 |
| 2227 | Wild Life Extreme | 22290 |
| 14485 | Night Raid | 100751 |
| 1519 MHz | Base Clock | 1515 MHz |
| 1582 MHz | Boost Clock | 1710 MHz |
| 384 | Shading Units | 2944 |
| 24 | Texture Mapping Units (TMUs) | 184 |
| 16 | Render Output Units (ROPs) | 64 |
| 3 | Compute Units (Pipelines) | 46 |
| No | Tensor Cores | 368 |
| No | Ray-tracing Cores | 46 |
| 48KB per cluster | L1 Cache | 64KB per cluster |
| 512KB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |