Quick/Comparisons
14 | Gaming | 18 |
23 | Workstation | 28 |
10 | AI/ML |
Compare with something else?
Compare Apple M3 GPU with another →14 |
95 | Energy Efficiency | 56 |
30 | Quick Comparison Final Score | 27 |
| — | Graphics Processor | TU116 (N18E-G0) |
| 1280 | Cores | 1536 |
| 80 / 40 | TMUs / ROPs | 96 / 48 |
| 155.27 | Blender GPU | 753.5 |
| — | Forza Horizon 5 | 47 |
| — | The Witcher 3 | 59 |
| — | Counter-Strike 2 | 88 |
| — | Far Cry 6 | 60 |
| — | Hogwarts Legacy | 33 |
| — | Call of Duty | 41 |
| — | Ghost of Tsushima | 31 |
| — | Cyberpunk 2077 | 39 |
| — | Tomb Raider | 65 |
| — | Average FPS | 51 |
| — | 1080p High | 66 |
| — | 1080p Ultra | 51 |
| — | 1440p Ultra | 36 |
| — | 4K Ultra | 19 |
| — | Margin of Error | Low |
| 30027 | GB6 Compute Score | 67761 |
| 60.3 img/sec | Background Blur | 119.1 img/sec |
| 40.8 img/sec | Face Detection | 64.8 img/sec |
| 1.21 Gpixels/sec | Horizon Detection | 2.58 Gpixels/sec |
| 1.64 Gpixels/sec | Edge Detection | 3.28 Gpixels/sec |
| 1.2 Gpixels/sec | Gaussian Blur | 3.37 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 0.88 Gpixels/sec |
| 102.6 Gpixels/sec | Stereo Matching | 300.1 Gpixels/sec |
| 3293.3 FPS | Particle Physics | 8599.6 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 10096 |
| — | G2D Mark | 473 |
| — | DirectX 11 | 87 FPS |
| — | DirectX 12 | 39 FPS |
| — | GPU Compute | 3651 Ops/s |
| 4120 | GB6 ML Single Precision | 8358 |
| 6992 | GB6 ML Half Precision | 6961 |
| 5638 | GB6 ML Quantized | 6020 |
| 1579 | Image Classification (SP) | 3378 |
| 2944 | Image Segmentation (HP) | 4732 |
| 4425 | Image Super Resolution (Q) | 8716 |
| 6661 | Face Detection (HP) | 7909 |
| 15020 | Pose Estimation (Q) | 35887 |
| 2984 | Text Classification (SP) | 1591 |
| 5876 | Machine Translation (HP) | 1912 |
| 1826 | Object Detection (SP) | 4195 |
| 9339 | Depth Estimation (Q) | 15599 |
| 22291 | Style Transfer (SP) | 70176 |
| Core ML | Framework | ONNX |
| CPU | Backend | DirectML |
| 55 GPixel/s | Pixel Fill Rate | 76 GPixel/s |
| 110 GTexel/s | Texture Fill Rate | 153 GTexel/s |
| 3.5 TFLOPS | FLOPS (FP32) | 4.9 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 6 GB |
| 6400 MHz | Memory Clock | 1500 MHz |
| 12800 Mbps | Effective Memory Speed | 12000 Mbps |
| 128-bit | Bus | 192-bit |
| No | ECC | No |
| 102.4 GB/s | Memory Bandwidth | 288 GB/s |
| Custom | Interface | PCIe 3.0 x16 |
| 15 W | TGP | 80 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 12 nm |
| — | Die Size | 284 mm² |
| 13.8 billion | Transistor Count | 6.6 billion |
| — | Transistor Density | 23.24 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.2 |
| — | OpenGL | 4.6 |
| — | OpenCL | 1.2 |
| — | CUDA | 7.5 |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.4 |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 31, 2023 | Released | April 23, 2019 |
| Laptop | Case | Laptop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Turing |
| — | GPU Codename | TU116 (N18E-G0) |
| -Apple M3or above | Recommended CPU | -Intel Core i5 10300Hor above |
| 3478 | Steel Nomad Lite Score | 5346 |
| — | Time Spy | 5596 |
| 13529 | Solar Bay | 18003 |
| — | Port Royal | 1507 |
| — | Fire Strike | 14839 |
| 8229 | Wild Life Extreme | 11402 |
| — | Night Raid | 60067 |
| 500 MHz | Base Clock | 1455 MHz |
| 1380 MHz | Boost Clock | 1590 MHz |
| 1280 | Shading Units | 1536 |
| 80 | Texture Mapping Units (TMUs) | 96 |
| 40 | Render Output Units (ROPs) | 48 |
| 160 | Compute Units (Pipelines) | 24 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | 64KB per cluster |
| — | L2 Cache | 1536KB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |