Quick/Comparisons
5 | Gaming | 16 |
10 | Workstation | 25 |
4 | AI/ML |
Compare with something else?
Compare GeForce MX350 with another →22 |
67 | Energy Efficiency | 100 |
17 | Quick Comparison Final Score | 33 |
| GP107 | Graphics Processor | Panther Lake |
| 640 | Cores | 1536 |
| 32 / 16 | TMUs / ROPs | 48 / 24 |
| 96.75 | Blender GPU | 1268.79 |
| - | Forza Horizon 5 | 38 |
| - | The Witcher 3 | 55 |
| 16 | Counter-Strike 2 | 60 |
| 15 | Far Cry 6 | 49 |
| - | Hogwarts Legacy | 21 |
| 21 | Call of Duty | 32 |
| - | Ghost of Tsushima | 25 |
| — | Cyberpunk 2077 | 33 |
| 9 | Tomb Raider | 52 |
| 10 | Average FPS | 41 |
| 15 | 1080p High | 52 |
| 10 | 1080p Ultra | 41 |
| - | 1440p Ultra | 29 |
| - | 4K Ultra | 14 |
| Medium | Margin of Error | Low |
| 15572 | GB6 Compute Score | 64546 |
| 40 img/sec | Background Blur | — |
| 18.9 img/sec | Face Detection | — |
| 0.59 Gpixels/sec | Horizon Detection | — |
| 0.88 Gpixels/sec | Edge Detection | — |
| 0.97 Gpixels/sec | Gaussian Blur | — |
| 0.15 Gpixels/sec | Feature Matching | — |
| 45.1 Gpixels/sec | Stereo Matching | — |
| 1531.6 FPS | Particle Physics | — |
| OpenCL | API | — |
| 2820 | G3D Mark Score | 9029 |
| 238 | G2D Mark | 786 |
| 20 FPS | DirectX 11 | 70 FPS |
| 15 FPS | DirectX 12 | 50 FPS |
| 1251 Ops/s | GPU Compute | 3702 Ops/s |
| 2424 | GB6 ML Single Precision | 11871 |
| 2615 | GB6 ML Half Precision | 20120 |
| 1827 | GB6 ML Quantized | 7879 |
| 949 | Image Classification (SP) | 5487 |
| 1407 | Image Segmentation (HP) | 16864 |
| 2693 | Image Super Resolution (Q) | 8788 |
| 2453 | Face Detection (HP) | 25029 |
| 8112 | Pose Estimation (Q) | 18852 |
| 1170 | Text Classification (SP) | 2115 |
| 1183 | Machine Translation (HP) | 4266 |
| 768 | Object Detection (SP) | 7449 |
| 3878 | Depth Estimation (Q) | 22207 |
| 20820 | Style Transfer (SP) | 95039 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 15-23 GPixel/s | Pixel Fill Rate | 60 GPixel/s |
| 30-47 GTexel/s | Texture Fill Rate | 120 GTexel/s |
| 1.2-1.9 TFLOPS | FLOPS (FP32) | 7.7 TFLOPS |
| GDDR5 | Memory Type | System Shared |
| 2 GB | Memory Size | — |
| 1752 MHz | Memory Clock | — |
| 7000 Mbps | Effective Memory Speed | — |
| 64-bit | Bus | — |
| — | ECC | No |
| 56 GB/s | Memory Bandwidth | — |
| PCIe 3.0 x4 | Interface | PCIe 5.0 |
| 15-30 W (configurable) | TGP | — |
| Samsung | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 3 nm |
| 132 mm² | Die Size | — |
| 3.3 billion | Transistor Count | — |
| 25 MTr/mm² | Transistor Density | — |
| 12 | DirectX | 12.1 |
| 1.2 | Vulkan | 1.4 |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3 |
| 6.1 | CUDA | — |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4 | DisplayPort | 2.1 |
| Nvidia | Vendor | Intel |
| Discrete | Build | Integrated |
| February 10, 2020 | Released | January 5, 2026 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Entry-level | Segment | Mid-range |
| Pascal | Architecture | Celestial |
| GP107 | GPU Codename | Panther Lake |
| -Intel Core i7 1165G7or above | Recommended CPU | -Intel Core Ultra X9 388Hor above |
| 967 | Steel Nomad Lite Score | 4242 |
| 1235 | Time Spy | 6595 |
| — | Solar Bay | 26399 |
| — | Port Royal | 3886 |
| 4234 | Fire Strike | 16770 |
| 2706 | Wild Life Extreme | 11707 |
| 17008 | Night Raid | 68498 |
| 747-1354 MHz (configurable) | Base Clock | 300 MHz |
| 936-1468 MHz (configurable) | Boost Clock | 2500 MHz |
| 640 | Shading Units | 1536 |
| 32 | Texture Mapping Units (TMUs) | 48 |
| 16 | Render Output Units (ROPs) | 24 |
| 5 | Compute Units (Pipelines) | 12 |
| No | Tensor Cores | — |
| No | Ray-tracing Cores | — |
| 48KB per cluster | L1 Cache | 64KB per cluster |
| 512KB shared | L2 Cache | 16MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |