Quick/Comparisons
5 | Gaming | 9 |
10 | Workstation | 12 |
4 | AI/ML |
Compare with something else?
Compare GeForce MX350 with another →13 |
67 | Energy Efficiency | 86 |
17 | Quick Comparison Final Score | 23 |
| GP107 | Graphics Processor | Krackan Point |
| 640 | Cores | 512 |
| 32 / 16 | TMUs / ROPs | 32 / 16 |
| 96.75 | Blender GPU | 193.82 |
| - | Forza Horizon 5 | 24 |
| - | The Witcher 3 | 18 |
| 16 | Counter-Strike 2 | 26 |
| 15 | Far Cry 6 | 26 |
| - | Hogwarts Legacy | 12 |
| 21 | Call of Duty | 27 |
| - | Ghost of Tsushima | 12 |
| — | Cyberpunk 2077 | 13 |
| 9 | Tomb Raider | 22 |
| 10 | Average FPS | 20 |
| 15 | 1080p High | 26 |
| 10 | 1080p Ultra | 20 |
| - | 1440p Ultra | 14 |
| - | 4K Ultra | - |
| Medium | Margin of Error | Low |
| 15572 | GB6 Compute Score | 22911 |
| 40 img/sec | Background Blur | 57.2 img/sec |
| 18.9 img/sec | Face Detection | 30.5 img/sec |
| 0.59 Gpixels/sec | Horizon Detection | 0.83 Gpixels/sec |
| 0.88 Gpixels/sec | Edge Detection | 1.16 Gpixels/sec |
| 0.97 Gpixels/sec | Gaussian Blur | 0.93 Gpixels/sec |
| 0.15 Gpixels/sec | Feature Matching | 0.35 Gpixels/sec |
| 45.1 Gpixels/sec | Stereo Matching | 97.8 Gpixels/sec |
| 1531.6 FPS | Particle Physics | 3933.5 FPS |
| OpenCL | API | OpenCL |
| 2820 | G3D Mark Score | 4877 |
| 238 | G2D Mark | 916 |
| 20 FPS | DirectX 11 | 37 FPS |
| 15 FPS | DirectX 12 | 24 FPS |
| 1251 Ops/s | GPU Compute | 2421 Ops/s |
| 2424 | GB6 ML Single Precision | 6947 |
| 2615 | GB6 ML Half Precision | 10338 |
| 1827 | GB6 ML Quantized | 5334 |
| 949 | Image Classification (SP) | 2022 |
| 1407 | Image Segmentation (HP) | 3987 |
| 2693 | Image Super Resolution (Q) | 6657 |
| 2453 | Face Detection (HP) | 10337 |
| 8112 | Pose Estimation (Q) | 28437 |
| 1170 | Text Classification (SP) | 2326 |
| 1183 | Machine Translation (HP) | 4011 |
| 768 | Object Detection (SP) | 1995 |
| 3878 | Depth Estimation (Q) | 12031 |
| 20820 | Style Transfer (SP) | 56710 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 15-23 GPixel/s | Pixel Fill Rate | 48 GPixel/s |
| 30-47 GTexel/s | Texture Fill Rate | 96 GTexel/s |
| 1.2-1.9 TFLOPS | FLOPS (FP32) | 3.1 TFLOPS |
| GDDR5 | Memory Type | System Shared |
| 2 GB | Memory Size | — |
| 1752 MHz | Memory Clock | — |
| 7000 Mbps | Effective Memory Speed | — |
| 64-bit | Bus | — |
| — | ECC | — |
| 56 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x4 | Interface | PCIe 4.0 x16 |
| 15-30 W (configurable) | TGP | 15-54 W (configurable) |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 4 nm |
| 132 mm² | Die Size | 233 mm² |
| 3.3 billion | Transistor Count | 34 billion |
| 25 MTr/mm² | Transistor Density | 145.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 2.1 |
| 6.1 | CUDA | No |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4 | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Integrated |
| February 10, 2020 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Generic |
| Entry-level | Segment | Mid-range |
| Pascal | Architecture | RDNA 3.5 |
| GP107 | GPU Codename | Krackan Point |
| -Intel Core i7 1165G7or above | Recommended CPU | -AMD Ryzen AI 7 350or above |
| 967 | Steel Nomad Lite Score | 2112 |
| 1235 | Time Spy | 2565 |
| — | Solar Bay | 11270 |
| — | Port Royal | 1103 |
| 4234 | Fire Strike | 6835 |
| 2706 | Wild Life Extreme | 5150 |
| 17008 | Night Raid | 29003 |
| 747-1354 MHz (configurable) | Base Clock | 600 MHz |
| 936-1468 MHz (configurable) | Boost Clock | 3000 MHz |
| 640 | Shading Units | 512 |
| 32 | Texture Mapping Units (TMUs) | 32 |
| 16 | Render Output Units (ROPs) | 16 |
| 5 | Compute Units (Pipelines) | 8 |
| No | Tensor Cores | No |
| No | Ray-tracing Cores | 8 |
| 48KB per cluster | L1 Cache | 512KB per cluster |
| 512KB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |