Quick/Comparisons
5 | Gaming | 44 |
10 | Workstation | 48 |
4 | AI/ML |
Compare with something else?
Compare GeForce MX350 with another →39 |
67 | Energy Efficiency | 27 |
17 | Quick Comparison Final Score | 44 |
| GP107 | Graphics Processor | TU102 |
| 640 | Cores | 4352 |
| 32 / 16 | TMUs / ROPs | 272 / 88 |
| 96.75 | Blender GPU | 3046.64 |
| - | Forza Horizon 5 | 101 |
| - | The Witcher 3 | 144 |
| 16 | Counter-Strike 2 | 199 |
| 15 | Far Cry 6 | 122 |
| - | Hogwarts Legacy | 82 |
| 21 | Call of Duty | 118 |
| - | Ghost of Tsushima | 78 |
| — | Cyberpunk 2077 | 98 |
| 9 | Tomb Raider | 155 |
| 10 | Average FPS | 122 |
| 15 | 1080p High | 145 |
| 10 | 1080p Ultra | 122 |
| - | 1440p Ultra | 92 |
| - | 4K Ultra | 52 |
| Medium | Margin of Error | Low |
| 15572 | GB6 Compute Score | 144745 |
| 40 img/sec | Background Blur | 211 img/sec |
| 18.9 img/sec | Face Detection | 141.3 img/sec |
| 0.59 Gpixels/sec | Horizon Detection | 6.24 Gpixels/sec |
| 0.88 Gpixels/sec | Edge Detection | 8.1 Gpixels/sec |
| 0.97 Gpixels/sec | Gaussian Blur | 9.22 Gpixels/sec |
| 0.15 Gpixels/sec | Feature Matching | 1.46 Gpixels/sec |
| 45.1 Gpixels/sec | Stereo Matching | 627.3 Gpixels/sec |
| 1531.6 FPS | Particle Physics | 16980.5 FPS |
| OpenCL | API | OpenCL |
| 2820 | G3D Mark Score | 21477 |
| 238 | G2D Mark | 927 |
| 20 FPS | DirectX 11 | 192 FPS |
| 15 FPS | DirectX 12 | 83 FPS |
| 1251 Ops/s | GPU Compute | 9906 Ops/s |
| 2424 | GB6 ML Single Precision | 19878 |
| 2615 | GB6 ML Half Precision | 31237 |
| 1827 | GB6 ML Quantized | 12663 |
| 949 | Image Classification (SP) | 8213 |
| 1407 | Image Segmentation (HP) | 19891 |
| 2693 | Image Super Resolution (Q) | 17598 |
| 2453 | Face Detection (HP) | 39785 |
| 8112 | Pose Estimation (Q) | 84003 |
| 1170 | Text Classification (SP) | 2062 |
| 1183 | Machine Translation (HP) | 4192 |
| 768 | Object Detection (SP) | 10444 |
| 3878 | Depth Estimation (Q) | 31856 |
| 20820 | Style Transfer (SP) | 207773 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 15-23 GPixel/s | Pixel Fill Rate | 136 GPixel/s |
| 30-47 GTexel/s | Texture Fill Rate | 420 GTexel/s |
| 1.2-1.9 TFLOPS | FLOPS (FP32) | 13.4 TFLOPS |
| GDDR5 | Memory Type | GDDR6 |
| 2 GB | Memory Size | 11 GB |
| 1752 MHz | Memory Clock | 1750 MHz |
| 7000 Mbps | Effective Memory Speed | 14000 Mbps |
| 64-bit | Bus | 352-bit |
| — | ECC | No |
| 56 GB/s | Memory Bandwidth | 616 GB/s |
| PCIe 3.0 x4 | Interface | PCIe 3.0 x16 |
| 15-30 W (configurable) | TGP | 250 W |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 12 nm |
| 132 mm² | Die Size | 754 mm² |
| 3.3 billion | Transistor Count | 18 billion |
| 25 MTr/mm² | Transistor Density | 23.87 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 10, 2020 | Released | September 27, 2018 |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | High-end |
| Pascal | Architecture | Turing |
| GP107 | GPU Codename | TU102 |
| -Intel Core i7 1165G7or above | Recommended CPU | -Intel Core i9 9900Kor above |
| 967 | Steel Nomad Lite Score | 14284 |
| 1235 | Time Spy | 14656 |
| — | Solar Bay | 64076 |
| — | Port Royal | 9109 |
| 4234 | Fire Strike | 35666 |
| 2706 | Wild Life Extreme | 29554 |
| 17008 | Night Raid | 115500 |
| 747-1354 MHz (configurable) | Base Clock | 1350 MHz |
| 936-1468 MHz (configurable) | Boost Clock | 1545 MHz |
| 640 | Shading Units | 4352 |
| 32 | Texture Mapping Units (TMUs) | 272 |
| 16 | Render Output Units (ROPs) | 88 |
| 5 | Compute Units (Pipelines) | 68 |
| No | Tensor Cores | 544 |
| No | Ray-tracing Cores | 68 |
| 48KB per cluster | L1 Cache | 64KB per cluster |
| 512KB shared | L2 Cache | 5632KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |