Quick/Comparisons
15 | Gaming | 78 |
25 | Workstation | 76 |
21 | AI/ML |
Compare with something else?
Compare Apple M4 GPU with another →66 |
95 | Energy Efficiency | 46 |
32 | Quick Comparison Final Score | 75 |
| Custom | Graphics Processor | AD103 |
| 1280 | Cores | 10240 |
| 80 / 40 | TMUs / ROPs | 320 / 112 |
| 1062.09 | Blender GPU | 8420.48 |
| — | Tomb Raider | 265 |
| — | Average FPS | 187 |
| — | Forza Horizon 5 | 171 |
| — | The Witcher 3 | 210 |
| — | Counter-Strike 2 | 223 |
| — | Far Cry 6 | 166 |
| — | Hogwarts Legacy | 137 |
| — | Call of Duty | 216 |
| — | Ghost of Tsushima | 122 |
| — | Cyberpunk 2077 | 177 |
| — | 1080p High | 221 |
| — | 1080p Ultra | 187 |
| — | 1440p Ultra | 149 |
| — | 4K Ultra | 87 |
| — | Margin of Error | Low |
| 37678 | GB6 Compute Score | 250691 |
| 72.2 img/sec | Background Blur | 279.5 img/sec |
| 48.3 img/sec | Face Detection | 220.1 img/sec |
| 1.4 Gpixels/sec | Horizon Detection | 11 Gpixels/sec |
| 1.94 Gpixels/sec | Edge Detection | 15.2 Gpixels/sec |
| 1.5 Gpixels/sec | Gaussian Blur | 16.2 Gpixels/sec |
| 0.53 Gpixels/sec | Feature Matching | 2.08 Gpixels/sec |
| 123.3 Gpixels/sec | Stereo Matching | 1370 Gpixels/sec |
| 4938.4 FPS | Particle Physics | 37199.7 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 34252 |
| — | G2D Mark | 1278 |
| — | DirectX 11 | 300 FPS |
| — | DirectX 12 | 134 FPS |
| — | GPU Compute | 19639 Ops/s |
| 10346 | GB6 ML Single Precision | 36883 |
| 11883 | GB6 ML Half Precision | 54286 |
| 11036 | GB6 ML Quantized | 28474 |
| 4874 | Image Classification (SP) | 12453 |
| 8168 | Image Segmentation (HP) | 34467 |
| 11983 | Image Super Resolution (Q) | 43534 |
| 17036 | Face Detection (HP) | 70300 |
| 31171 | Pose Estimation (Q) | 242331 |
| 2964 | Text Classification (SP) | 3767 |
| 3410 | Machine Translation (HP) | 6614 |
| 5112 | Object Detection (SP) | 18301 |
| 22700 | Depth Estimation (Q) | 66477 |
| 60872 | Style Transfer (SP) | 417906 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 59 GPixel/s | Pixel Fill Rate | 286 GPixel/s |
| 118 GTexel/s | Texture Fill Rate | 816 GTexel/s |
| 3.8 TFLOPS | FLOPS (FP32) | 52.2 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 16 GB |
| 7500 MHz | Memory Clock | 1438 MHz |
| 15000 Mbps | Effective Memory Speed | 23000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 120 GB/s | Memory Bandwidth | 736.3 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| 18 W | TGP | 320 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 379 mm² |
| 28 billion | Transistor Count | 45 billion |
| — | Transistor Density | 118.73 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| — | DisplayPort | 1.4a |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| May 7, 2024 | Released | January 31, 2024 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | Ada Lovelace |
| Custom | GPU Codename | AD103 |
| -Apple M4 (10-Core)or above | Recommended CPU | -Intel Core i7 14700Kor above |
| 4097 | Steel Nomad Lite Score | 30711 |
| — | Time Spy | 28279 |
| 16545 | Solar Bay | 138998 |
| — | Port Royal | 18348 |
| — | Fire Strike | 63714 |
| 9591 | Wild Life Extreme | 60015 |
| — | Night Raid | 180412 |
| 500 MHz | Base Clock | 2295 MHz |
| 1470 MHz | Boost Clock | 2550 MHz |
| 1280 | Shading Units | 10240 |
| 80 | Texture Mapping Units (TMUs) | 320 |
| 40 | Render Output Units (ROPs) | 112 |
| 160 | Compute Units (Pipelines) | 80 |
| — | Tensor Cores | 320 |
| — | Ray-tracing Cores | 80 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |