Quick/Comparisons
The Apple M3 Pro GPU (18-core) takes the lead in gaming with a score of 19, thanks to its Apple M GPU architecture and custom codename.
The Apple M3 Pro GPU (18-core) excels in content creation with a score of 27, outperforming the Intel Arc 130V by 11 points.
The Apple M3 Pro GPU (18-core) leads in AI & Machine Learning with a score of 24, thanks to its custom interface and system shared memory.
19 | Gaming | 17 |
27 | Workstation | 16 |
24 | AI/ML |
Compare with something else?
Compare Apple M3 Pro with another →14 |
90 | Energy Efficiency | 92 |
34 | Quick Comparison Final Score | 29 |
| Custom | Graphics Processor | Lunar Lake iGPU |
| 2304 | Cores | 896 |
| 144 / 72 | TMUs / ROPs | — |
| 1678.22 | Blender GPU | 582.72 |
| — | 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 | — |
| 43099 | GB6 Compute Score | 25557 |
| 82.1 img/sec | Background Blur | 64.5 img/sec |
| 53.6 img/sec | Face Detection | 34.5 img/sec |
| 1.82 Gpixels/sec | Horizon Detection | 0.74 Gpixels/sec |
| 2.59 Gpixels/sec | Edge Detection | 1.02 Gpixels/sec |
| 1.84 Gpixels/sec | Gaussian Blur | 1.27 Gpixels/sec |
| 0.48 Gpixels/sec | Feature Matching | 0.34 Gpixels/sec |
| 148.6 Gpixels/sec | Stereo Matching | 83.6 Gpixels/sec |
| 4893.9 FPS | Particle Physics | 3402.8 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 4494 |
| — | G2D Mark | 618 |
| — | DirectX 11 | 32 FPS |
| — | DirectX 12 | 26 FPS |
| — | GPU Compute | 2490 Ops/s |
| 11804 | GB6 ML Single Precision | 7794 |
| 13606 | GB6 ML Half Precision | 15672 |
| 12673 | GB6 ML Quantized | 5126 |
| 5578 | Image Classification (SP) | 4265 |
| 9924 | Image Segmentation (HP) | 13719 |
| 13323 | Image Super Resolution (Q) | 5154 |
| 19900 | Face Detection (HP) | 18675 |
| 35730 | Pose Estimation (Q) | 14874 |
| 2904 | Text Classification (SP) | 1399 |
| 4985 | Machine Translation (HP) | 3623 |
| 5496 | Object Detection (SP) | 5223 |
| 23344 | Depth Estimation (Q) | 11851 |
| 78342 | Style Transfer (SP) | 45215 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 99 GPixel/s | Pixel Fill Rate | — |
| 199 GTexel/s | Texture Fill Rate | — |
| 6.4 TFLOPS | FLOPS (FP32) | 3.3 TFLOPS |
| System Shared | Memory Type | System Shared |
| — | Memory Size | — |
| 6400 MHz | Memory Clock | — |
| 12800 Mbps | Effective Memory Speed | — |
| 192-bit | Bus | — |
| No | ECC | No |
| 153.6 GB/s | Memory Bandwidth | — |
| Custom | Interface | Ring Bus |
| 30 W | TGP | 30 W |
| TSMC | Manufacturing | Intel |
| 3 nm | Fabrication Process | 3 nm |
| — | Die Size | — |
| 25.2 billion | Transistor Count | — |
| — | Transistor Density | — |
| — | DirectX | 12.2 |
| — | Vulkan | — |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | No |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| — | DisplayPort | 2.1 |
| Apple | Vendor | Intel |
| Integrated | Build | Integrated |
| October 31, 2023 | Released | September 4, 2024 |
| Laptop | Case | Laptop |
| Professional | Purpose | Generic |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Xe2 |
| Custom | GPU Codename | Lunar Lake iGPU |
| -Apple M3 Proor above | Recommended CPU | -Intel Core Ultra 5 226Vor above |
| 6092 | Steel Nomad Lite Score | — |
| — | Time Spy | — |
| 22577 | Solar Bay | — |
| — | Port Royal | — |
| — | Fire Strike | — |
| 14001 | Wild Life Extreme | — |
| — | Night Raid | — |
| 500 MHz | Base Clock | 600 MHz |
| 1380 MHz | Boost Clock | 1850 MHz |
| 2304 | Shading Units | 896 |
| 144 | Texture Mapping Units (TMUs) | — |
| 72 | Render Output Units (ROPs) | — |
| 288 | Compute Units (Pipelines) | — |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | 7 |
| — | L1 Cache | — |
| — | L2 Cache | — |
| 2 IPC | Instructions Per Cycle | 2 IPC |