Quick/Comparisons
The GeForce RTX 5070 Ti's superior gaming performance, with a score of 76, makes it the clear winner in this use case. Its large 16GB memory pool and Blackwell 2.0 architecture contribute to its strong gaming capabilities.
Both GPUs have strong workstation capabilities, with the Apple A18 Pro GPU scoring 21 and the GeForce RTX 5070 Ti scoring 74. Their scores are close enough to be considered a tie.
The GeForce RTX 5070 Ti's score of 66 in AI/ML workloads is significantly higher than the Apple A18 Pro GPU's score of 14, making it the winner in this use case. Its Blackwell 2.0 architecture and 16GB GDDR7 memory contribute to its strong AI/ML capabilities.
11 | Gaming | 76 |
21 | Workstation | 74 |
14 | AI/ML | 66 |
96 | Energy Efficiency | 49 |
28 | Quick Comparison Final Score | 74 |
| Custom | Graphics Processor | GB203-200-A1 |
| 768 | Cores | 8960 |
| 40 | TMUs / ROPs | 280 / 96 |
| — | 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 |
| 31229 | GB6 Compute Score | 240508 |
| — | Background Blur | 297.9 img/sec |
| — | Face Detection | 218.6 img/sec |
| — | Horizon Detection | 10.1 Gpixels/sec |
| — | Edge Detection | 13.9 Gpixels/sec |
| — | Gaussian Blur | 14.8 Gpixels/sec |
| — | Feature Matching | 2.03 Gpixels/sec |
| — | Stereo Matching | 1290 Gpixels/sec |
| — | Particle Physics | 35438.3 FPS |
| — | API | OpenCL |
| — | G3D Mark Score | 32425 |
| — | G2D Mark | 1329 |
| — | DirectX 11 | 304 FPS |
| — | DirectX 12 | 126 FPS |
| — | GPU Compute | 18089 Ops/s |
| 6982 | GB6 ML Single Precision | 36504 |
| 8282 | GB6 ML Half Precision | 64459 |
| 7200 | GB6 ML Quantized | 27312 |
| 3264 | Image Classification (SP) | 14913 |
| 4550 | Image Segmentation (HP) | 45199 |
| 6705 | Image Super Resolution (Q) | 39360 |
| 11770 | Face Detection (HP) | 84188 |
| 15548 | Pose Estimation (Q) | 161400 |
| 3678 | Text Classification (SP) | 4010 |
| 5678 | Machine Translation (HP) | 7973 |
| 3360 | Object Detection (SP) | 18934 |
| 13468 | Depth Estimation (Q) | 67761 |
| 31541 | Style Transfer (SP) | 335879 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| — | Pixel Fill Rate | 235 GPixel/s |
| 60 GTexel/s | Texture Fill Rate | 687 GTexel/s |
| 2.3 TFLOPS | FLOPS (FP32) | 43.9 TFLOPS |
| System Shared | Memory Type | GDDR7 |
| — | Memory Size | 16 GB |
| 7500 MHz | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 28000 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| — | Memory Bandwidth | 896 GB/s |
| Custom | Interface | PCIe 5.0 x16 |
| — | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 4 nm |
| — | Die Size | 378 mm² |
| — | Transistor Count | 45.6 billion |
| — | Transistor Density | 120.63 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 | Desktop |
| Generic | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| Apple M GPU | Architecture | Blackwell 2.0 |
| Custom | GPU Codename | GB203-200-A1 |
| -Apple A18 Pro (MacBook)or above | Recommended CPU | -Intel Core Ultra 5 245Kor above |
| 1795 | Steel Nomad Lite Score | 29989 |
| — | Time Spy | 27815 |
| 7273 | Solar Bay | 136964 |
| — | Port Royal | 19613 |
| — | Fire Strike | 67382 |
| 3982 | Wild Life Extreme | 57734 |
| — | Night Raid | 189734 |
| — | Base Clock | 2295 MHz |
| 1490 MHz | Boost Clock | 2452 MHz |
| 768 | Shading Units | 8960 |
| 40 | Texture Mapping Units (TMUs) | 280 |
| — | Render Output Units (ROPs) | 96 |
| 128 | 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 A18 Pro with another →