Quick/Comparisons
A mid-range Apple M5 Pro GPU (20-core) integrated graphics with modest AI/ML performance (50/100), excellent energy efficiency. Suited for 1080p gaming and everyday tasks.
| Gaming | 27 /100 |
| Workstation | 38 /100 |
| AI/ML | 50 /100 |
| Energy Efficiency | 94 |
Looking for more comparisons?
Compare Apple M5 →| Quick Comparison Final Score | 43 /100 |
| Graphics Processor | Custom |
| Cores | 2560 |
| TMUs / ROPs | 160 / 80 |
| Blender GPU | 4282.65 |
| Forza Horizon 5 | — |
| The Witcher 3 | — |
| Counter-Strike 2 | — |
| Far Cry 6 | — |
| Hogwarts Legacy | — |
| Call of Duty | — |
| Ghost of Tsushima | — |
| Cyberpunk 2077 | — |
| Tomb Raider | — |
| Average FPS | — |
| 1080p High | — |
| 1080p Ultra | — |
| 1440p Ultra | — |
| 4K Ultra | — |
| Margin of Error | — |
| GB6 Compute Score | 87961 |
| Background Blur | 177.6 img/sec |
| Face Detection | 114.5 img/sec |
| Horizon Detection | 3.19 Gpixels/sec |
| Edge Detection | 4.45 Gpixels/sec |
| Gaussian Blur | 4.59 Gpixels/sec |
| Feature Matching | 0.96 Gpixels/sec |
| Stereo Matching | 250.4 Gpixels/sec |
| Particle Physics | 12529.9 FPS |
| API | OpenCL |
| G3D Mark Score | — |
| G2D Mark | — |
| DirectX 11 | — |
| DirectX 12 | — |
| GPU Compute | — |
| GB6 ML Single Precision | 20378 |
| GB6 ML Half Precision | 35427 |
| GB6 ML Quantized | 34316 |
| Image Classification (SP) | 8870 |
| Image Segmentation (HP) | 28795 |
| Image Super Resolution (Q) | 34820 |
| Face Detection (HP) | 55699 |
| Pose Estimation (Q) | 212347 |
| Text Classification (SP) | 3018 |
| Machine Translation (HP) | 9102 |
| Object Detection (SP) | 8163 |
| Depth Estimation (Q) | 70908 |
| Style Transfer (SP) | 152297 |
| Framework | Core ML |
| Backend | GPU |
| Pixel Fill Rate | 130 GPixel/s |
| Texture Fill Rate | 259 GTexel/s |
| FLOPS (FP32) | 8.3 TFLOPS |
| Memory Type | System Shared |
| Memory Size | — |
| Memory Clock | 9600 MHz |
| Effective Memory Speed | — |
| Bus | 256-bit |
| ECC | No |
| Memory Bandwidth | 307 GB/s |
| Interface | Custom |
| TGP | 28 W |
| Manufacturing | TSMC |
| Fabrication Process | 3 nm |
| Die Size | — |
| Transistor Count | 28 billion |
| Transistor Density | — |
| DirectX | — |
| Vulkan | — |
| OpenGL | — |
| OpenCL | — |
| CUDA | — |
| Ray Tracing | Yes |
| DLSS | No |
| DisplayPort | — |
| Vendor | Apple |
| Build | Integrated |
| Released | March 3, 2026 |
| Case | Laptop |
| Purpose | Professional |
| Segment | Mid-range |
| Architecture | Apple M GPU |
| GPU Codename | Custom |
| Recommended CPU | -Apple M5 Pro (18-Core)or above |
| Steel Nomad Lite Score | 10059 |
| Time Spy | — |
| Solar Bay | 46898 |
| Port Royal | — |
| Fire Strike | — |
| Wild Life Extreme | 23773 |
| Night Raid | — |
| Base Clock | — |
| Boost Clock | 1620 MHz |
| Shading Units | 2560 |
| Texture Mapping Units (TMUs) | 160 |
| Render Output Units (ROPs) | 80 |
| Compute Units (Pipelines) | 320 |
| Tensor Cores | — |
| Ray-tracing Cores | — |
| L1 Cache | — |
| L2 Cache | — |
| Instructions Per Cycle | 2 IPC |
84/100