Quick/Comparisons
The GeForce GTX 970 takes the lead in gaming performance with a score of 12, outpacing the Apple M2 GPU's 9.
The Apple M2 GPU's 23 in content creation surpasses the GeForce GTX 970's 21, thanks to its workstation capabilities.
The Apple M2 GPU's 12 in AI/ML performance edges out the GeForce GTX 970's 11, despite both being relatively low scores.
9 | Gaming | 12 |
23 | Workstation | 21 |
12 | AI/ML |
Compare with something else?
Compare Apple M2 GPU with another →11 |
91 | Energy Efficiency | 10 |
27 | Quick Comparison Final Score | 15 |
| — | Graphics Processor | GM204 |
| 1024 | Cores | 1664 |
| 64 / 32 | TMUs / ROPs | 104 / 56 |
| 301.33 | Blender GPU | 286.89 |
| — | Forza Horizon 5 | 32 |
| — | The Witcher 3 | 35 |
| — | Counter-Strike 2 | 57 |
| — | Far Cry 6 | 39 |
| — | Hogwarts Legacy | 18 |
| — | Call of Duty | 31 |
| — | Ghost of Tsushima | 17 |
| — | Cyberpunk 2077 | 24 |
| — | Tomb Raider | 44 |
| — | Average FPS | 33 |
| — | 1080p High | 44 |
| — | 1080p Ultra | 33 |
| — | 1440p Ultra | 23 |
| — | 4K Ultra | 12 |
| — | Margin of Error | Low |
| 29705 | GB6 Compute Score | 28989 |
| 58.7 img/sec | Background Blur | 77.1 img/sec |
| 35.2 img/sec | Face Detection | 38.1 img/sec |
| 1.1 Gpixels/sec | Horizon Detection | 1.28 Gpixels/sec |
| 1.82 Gpixels/sec | Edge Detection | 2.08 Gpixels/sec |
| 1.2 Gpixels/sec | Gaussian Blur | 1.85 Gpixels/sec |
| 0.37 Gpixels/sec | Feature Matching | 0.17 Gpixels/sec |
| 96 Gpixels/sec | Stereo Matching | 92.9 Gpixels/sec |
| 3825.9 FPS | Particle Physics | 2443 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 9639 |
| — | G2D Mark | 763 |
| — | DirectX 11 | 71 FPS |
| — | DirectX 12 | 41 FPS |
| — | GPU Compute | 4080 Ops/s |
| 6206 | GB6 ML Single Precision | 6791 |
| 6893 | GB6 ML Half Precision | 6738 |
| 6515 | GB6 ML Quantized | 5128 |
| 3242 | Image Classification (SP) | 1852 |
| 4890 | Image Segmentation (HP) | 3622 |
| 7149 | Image Super Resolution (Q) | 8987 |
| 10340 | Face Detection (HP) | 7074 |
| 21268 | Pose Estimation (Q) | 43726 |
| 2268 | Text Classification (SP) | 1446 |
| 1122 | Machine Translation (HP) | 1576 |
| 3007 | Object Detection (SP) | 2425 |
| 13941 | Depth Estimation (Q) | 12902 |
| 35943 | Style Transfer (SP) | 86714 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 45 GPixel/s | Pixel Fill Rate | 66 GPixel/s |
| 89 GTexel/s | Texture Fill Rate | 123 GTexel/s |
| 2.9 TFLOPS | FLOPS (FP32) | 3.9 TFLOPS |
| System Shared | Memory Type | GDDR5 |
| — | Memory Size | 4 GB |
| 6400 MHz | Memory Clock | 1753 MHz |
| 12800 Mbps | Effective Memory Speed | 7000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 102.4 GB/s | Memory Bandwidth | 224.4 GB/s |
| Custom | Interface | PCIe 3.0 x16 |
| 15 W | TGP | 148 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 28 nm |
| — | Die Size | 398 mm² |
| 11.6 billion | Transistor Count | 5 billion |
| — | Transistor Density | 12.56 MTr/mm² |
| — | DirectX | 12 |
| — | Vulkan | 1.3 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 5.2 |
| No | Ray Tracing | No |
| No | DLSS | No |
| — | DisplayPort | 1.2 |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| June 6, 2022 | Released | September 19, 2014 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Maxwell 2.0 |
| — | GPU Codename | GM204 |
| -Apple M2or above | Recommended CPU | — |
| 2312 | Steel Nomad Lite Score | 3577 |
| — | Time Spy | 3666 |
| 7310 | Solar Bay | — |
| — | Port Royal | 4353 |
| — | Fire Strike | 12102 |
| 5675 | Wild Life Extreme | 6972 |
| — | Night Raid | 47591 |
| 500 MHz | Base Clock | 1050 MHz |
| 1398 MHz | Boost Clock | 1178 MHz |
| 1024 | Shading Units | 1664 |
| 64 | Texture Mapping Units (TMUs) | 104 |
| 32 | Render Output Units (ROPs) | 56 |
| 128 | Compute Units (Pipelines) | 13 |
| — | Tensor Cores | No |
| — | Ray-tracing Cores | No |
| — | L1 Cache | 48KB per cluster |
| — | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |