Quick/Comparisons
11 | Gaming | 43 |
21 | Workstation | 44 |
14 | AI/ML |
Compare with something else?
Compare Apple A18 Pro with another →35 |
96 | Energy Efficiency | 35 |
28 | Quick Comparison Final Score | 42 |
| Custom | Graphics Processor | GA104 |
| 768 | Cores | 5888 |
| 40 | TMUs / ROPs | 184 / 96 |
| — | Blender GPU | 3368.42 |
| — | Forza Horizon 5 | 99 |
| — | The Witcher 3 | 143 |
| — | Counter-Strike 2 | 194 |
| — | Far Cry 6 | 121 |
| — | Hogwarts Legacy | 80 |
| — | Call of Duty | 113 |
| — | Ghost of Tsushima | 74 |
| — | Cyberpunk 2077 | 94 |
| — | Tomb Raider | 153 |
| — | Average FPS | 119 |
| — | 1080p High | 141 |
| — | 1080p Ultra | 119 |
| — | 1440p Ultra | 88 |
| — | 4K Ultra | 50 |
| — | Margin of Error | Low |
| 31229 | GB6 Compute Score | 126195 |
| — | Background Blur | 161.6 img/sec |
| — | Face Detection | 117.2 img/sec |
| — | Horizon Detection | 5.89 Gpixels/sec |
| — | Edge Detection | 8.05 Gpixels/sec |
| — | Gaussian Blur | 6.65 Gpixels/sec |
| — | Feature Matching | 1.25 Gpixels/sec |
| — | Stereo Matching | 550.6 Gpixels/sec |
| — | Particle Physics | 17613.1 FPS |
| — | API | OpenCL |
| — | G3D Mark Score | 22128 |
| — | G2D Mark | 1005 |
| — | DirectX 11 | 182 FPS |
| — | DirectX 12 | 84 FPS |
| — | GPU Compute | 11062 Ops/s |
| 6982 | GB6 ML Single Precision | 19789 |
| 8282 | GB6 ML Half Precision | 33013 |
| 7200 | GB6 ML Quantized | 12443 |
| 3264 | Image Classification (SP) | 7624 |
| 4550 | Image Segmentation (HP) | 23420 |
| 6705 | Image Super Resolution (Q) | 17898 |
| 11770 | Face Detection (HP) | 40535 |
| 15548 | Pose Estimation (Q) | 83624 |
| 3678 | Text Classification (SP) | 2724 |
| 5678 | Machine Translation (HP) | 4481 |
| 3360 | Object Detection (SP) | 10304 |
| 13468 | Depth Estimation (Q) | 30418 |
| 31541 | Style Transfer (SP) | 180089 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| — | Pixel Fill Rate | 166 GPixel/s |
| 60 GTexel/s | Texture Fill Rate | 317 GTexel/s |
| 2.3 TFLOPS | FLOPS (FP32) | 20.3 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| 7500 MHz | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 14000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| — | Memory Bandwidth | 448 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| — | TGP | 220 W |
| TSMC | Manufacturing | Samsung |
| 3 nm | Fabrication Process | 8 nm |
| — | Die Size | 392 mm² |
| — | Transistor Count | 17 billion |
| — | Transistor Density | 43.37 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| September 9, 2024 | Released | October 22, 2020 |
| Laptop | Case | Desktop |
| Generic | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Ampere |
| Custom | GPU Codename | GA104 |
| -Apple A18 Pro (MacBook)or above | Recommended CPU | -Intel Core i7 12700Kor above |
| 1795 | Steel Nomad Lite Score | 14153 |
| — | Time Spy | 13643 |
| 7273 | Solar Bay | 64426 |
| — | Port Royal | 8311 |
| — | Fire Strike | 34054 |
| 3982 | Wild Life Extreme | 28486 |
| — | Night Raid | 122039 |
| — | Base Clock | 1500 MHz |
| 1490 MHz | Boost Clock | 1725 MHz |
| 768 | Shading Units | 5888 |
| 40 | Texture Mapping Units (TMUs) | 184 |
| — | Render Output Units (ROPs) | 96 |
| 128 | Compute Units (Pipelines) | 46 |
| — | Tensor Cores | 184 |
| — | Ray-tracing Cores | 46 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |