Quick/Comparisons
The GeForce RTX 5070 Ti outperforms the Apple M2 Pro GPU (19-core) in gaming due to its significantly higher score of 76. Its large 16GB memory pool and hardware ray tracing support contribute to its superior gaming performance.
Both the Apple M2 Pro GPU (19-core) and the GeForce RTX 5070 Ti have similar scores in content creation, with the Apple M2 Pro GPU (19-core) scoring 29 and the GeForce RTX 5070 Ti scoring 74. This indicates a close competition between the two GPUs in this use case.
The GeForce RTX 5070 Ti outperforms the Apple M2 Pro GPU (19-core) in AI and machine learning due to its higher score of 66. Its Blackwell 2.0 architecture and 16GB GDDR7 memory contribute to its superior performance in this use case.
16 | Gaming | 76 |
29 | Workstation | 74 |
21 | AI/ML | 66 |
86 | Energy Efficiency | 49 |
32 | Quick Comparison Final Score | 74 |
| — | Graphics Processor | GB203-200-A1 |
| 2432 | Cores | 8960 |
| 152 / 76 | TMUs / ROPs | 280 / 96 |
| 890.28 | Blender GPU | 7584.67 |
| — | Forza Horizon 5 | 166 |
| — | The Witcher 3 | 213 |
| — | Counter-Strike 2 | 219 |
| — | Far Cry 6 | 159 |
| — | Hogwarts Legacy | 135 |
| — | Call of Duty | 205 |
| — | Ghost of Tsushima | 121 |
| — | Cyberpunk 2077 | 174 |
| — | Tomb Raider | 260 |
| — | Average FPS | 184 |
| — | 1080p High | 217 |
| — | 1080p Ultra | 184 |
| — | 1440p Ultra | 148 |
| — | 4K Ultra | 86 |
| — | Margin of Error | Low |
| 49366 | GB6 Compute Score | 240508 |
| 89.7 img/sec | Background Blur | 297.9 img/sec |
| 58 img/sec | Face Detection | 218.6 img/sec |
| 1.94 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 3.26 Gpixels/sec | Edge Detection | 13.9 Gpixels/sec |
| 2.19 Gpixels/sec | Gaussian Blur | 14.8 Gpixels/sec |
| 0.55 Gpixels/sec | Feature Matching | 2.03 Gpixels/sec |
| 163 Gpixels/sec | Stereo Matching | 1290 Gpixels/sec |
| 6139.2 FPS | Particle Physics | 35438.3 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 32425 |
| — | G2D Mark | 1329 |
| — | DirectX 11 | 304 FPS |
| — | DirectX 12 | 126 FPS |
| — | GPU Compute | 18089 Ops/s |
| 11188 | GB6 ML Single Precision | 36504 |
| 12072 | GB6 ML Half Precision | 64459 |
| 10754 | GB6 ML Quantized | 27312 |
| 5279 | Image Classification (SP) | 14913 |
| 8089 | Image Segmentation (HP) | 45199 |
| 15007 | Image Super Resolution (Q) | 39360 |
| 19212 | Face Detection (HP) | 84188 |
| 44046 | Pose Estimation (Q) | 161400 |
| 2280 | Text Classification (SP) | 4010 |
| 1972 | Machine Translation (HP) | 7973 |
| 4941 | Object Detection (SP) | 18934 |
| 22209 | Depth Estimation (Q) | 67761 |
| 79898 | Style Transfer (SP) | 335879 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 106 GPixel/s | Pixel Fill Rate | 235 GPixel/s |
| 212 GTexel/s | Texture Fill Rate | 687 GTexel/s |
| 6.8 TFLOPS | FLOPS (FP32) | 43.9 TFLOPS |
| System Shared | Memory Type | GDDR7 |
| — | Memory Size | 16 GB |
| 6400 MHz | Memory Clock | 1750 MHz |
| 12800 Mbps | Effective Memory Speed | 28000 Mbps |
| 256-bit | Bus | 256-bit |
| No | ECC | No |
| 204.8 GB/s | Memory Bandwidth | 896 GB/s |
| Custom | Interface | PCIe 5.0 x16 |
| 35 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 4 nm |
| — | Die Size | 378 mm² |
| 26 billion | Transistor Count | 45.6 billion |
| — | Transistor Density | 120.63 MTr/mm² |
| — | DirectX | 12.2 |
| — | Vulkan | 1.4 |
| — | OpenGL | 4.6 |
| — | OpenCL | 3 |
| — | CUDA | 12 |
| No | Ray Tracing | Yes |
| No | DLSS | DLSS 4 |
| — | DisplayPort | 2.1b |
| Apple | Vendor | Nvidia |
| Integrated | Build | Discrete |
| January 17, 2023 | Released | January 7, 2025 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Apple M GPU | Architecture | Blackwell 2.0 |
| — | GPU Codename | GB203-200-A1 |
| -Apple M2 Proor above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 5120 | Steel Nomad Lite Score | 29989 |
| — | Time Spy | 27815 |
| 16208 | Solar Bay | 136964 |
| — | Port Royal | 19613 |
| — | Fire Strike | 67382 |
| 12727 | Wild Life Extreme | 57734 |
| — | Night Raid | 189734 |
| 450 MHz | Base Clock | 2295 MHz |
| 1398 MHz | Boost Clock | 2452 MHz |
| 2432 | Shading Units | 8960 |
| 152 | Texture Mapping Units (TMUs) | 280 |
| 76 | Render Output Units (ROPs) | 96 |
| 304 | Compute Units (Pipelines) | 70 |
| — | Tensor Cores | 280 |
| — | Ray-tracing Cores | 70 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare Apple M2 Pro with another →