Quick/Comparisons
11 | Gaming | 45 |
21 | Workstation | 45 |
14 | AI/ML |
Compare with something else?
Compare Apple A18 Pro with another →39 |
96 | Energy Efficiency | 65 |
28 | Quick Comparison Final Score | 48 |
| Custom | Graphics Processor | GB206-300 |
| 768 | Cores | 4608 |
| 40 | TMUs / ROPs | 144 / 48 |
| — | Blender GPU | 4007.35 |
| — | Forza Horizon 5 | 96 |
| — | The Witcher 3 | 137 |
| — | Counter-Strike 2 | 195 |
| — | Far Cry 6 | 116 |
| — | Hogwarts Legacy | 79 |
| — | Call of Duty | 110 |
| — | Ghost of Tsushima | 73 |
| — | Cyberpunk 2077 | 92 |
| — | Tomb Raider | 149 |
| — | Average FPS | 116 |
| — | 1080p High | 140 |
| — | 1080p Ultra | 116 |
| — | 1440p Ultra | 88 |
| — | 4K Ultra | 51 |
| — | Margin of Error | Low |
| 31229 | GB6 Compute Score | 134209 |
| — | Background Blur | 213.4 img/sec |
| — | Face Detection | 130.4 img/sec |
| — | Horizon Detection | 4.89 Gpixels/sec |
| — | Edge Detection | 6.23 Gpixels/sec |
| — | Gaussian Blur | 7.41 Gpixels/sec |
| — | Feature Matching | 1.46 Gpixels/sec |
| — | Stereo Matching | 661.9 Gpixels/sec |
| — | Particle Physics | 19395.6 FPS |
| — | API | OpenCL |
| — | G3D Mark Score | 19173 |
| — | G2D Mark | 884 |
| — | DirectX 11 | 186 FPS |
| — | DirectX 12 | 91 FPS |
| — | GPU Compute | 7114 Ops/s |
| 6982 | GB6 ML Single Precision | 22022 |
| 8282 | GB6 ML Half Precision | 40929 |
| 7200 | GB6 ML Quantized | 17069 |
| 3264 | Image Classification (SP) | 8984 |
| 4550 | Image Segmentation (HP) | 26270 |
| 6705 | Image Super Resolution (Q) | 24606 |
| 11770 | Face Detection (HP) | 48283 |
| 15548 | Pose Estimation (Q) | 98180 |
| 3678 | Text Classification (SP) | 3260 |
| 5678 | Machine Translation (HP) | 5770 |
| 3360 | Object Detection (SP) | 11172 |
| 13468 | Depth Estimation (Q) | 43305 |
| 31541 | Style Transfer (SP) | 165555 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| — | Pixel Fill Rate | 68-121 GPixel/s |
| 60 GTexel/s | Texture Fill Rate | 203-363 GTexel/s |
| 2.3 TFLOPS | FLOPS (FP32) | 13-23.2 TFLOPS |
| System Shared | Memory Type | GDDR7 |
| — | Memory Size | 8 GB |
| 7500 MHz | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 24000 Mbps |
| 128-bit | Bus | 128-bit |
| No | ECC | No |
| — | Memory Bandwidth | 384 GB/s |
| Custom | Interface | PCIe 5.0 x16 |
| — | TGP | 50-125 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 4 nm |
| — | Die Size | 181 mm² |
| — | Transistor Count | 21.9 billion |
| — | Transistor Density | 120.99 MTr/mm² |
| — | DirectX | 12.2 |
| — | Vulkan | 1.4 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 12 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| — | DisplayPort | 2.1b |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| September 9, 2024 | Released | January 7, 2025 |
| Laptop | Case | Laptop |
| Generic | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Blackwell 2.0 |
| Custom | GPU Codename | GB206-300 |
| -Apple A18 Pro (MacBook)or above | Recommended CPU | -Intel Core Ultra 7 255HXor above |
| 1795 | Steel Nomad Lite Score | 13896 |
| — | Time Spy | 13563 |
| 7273 | Solar Bay | 59662 |
| — | Port Royal | 8648 |
| — | Fire Strike | 35860 |
| 3982 | Wild Life Extreme | 24526 |
| — | Night Raid | 125756 |
| — | Base Clock | 890-1410 MHz (configurable) |
| 1490 MHz | Boost Clock | 1410-2520 MHz (configurable) |
| 768 | Shading Units | 4608 |
| 40 | Texture Mapping Units (TMUs) | 144 |
| — | Render Output Units (ROPs) | 48 |
| 128 | Compute Units (Pipelines) | 36 |
| — | Tensor Cores | 144 |
| — | Ray-tracing Cores | 36 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 32MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |