Quick/Comparisons
The GeForce RTX 4080 leads by a significant margin of 36 points, making it the clear winner for gaming performance. Its 80 score is nearly double that of the Apple M5 Max GPU (40-core).
Although the GeForce RTX 4080 has a slight edge, the Apple M5 Max GPU (40-core) still performs well in content creation tasks, making it a suitable choice for this use case. However, the RTX 4080's 17-point lead is not substantial enough to declare it the clear winner.
Both GPUs tie in AI and machine learning tasks, with identical scores of 66. This suggests that they offer comparable performance in this area.
44 | Gaming | 80 |
54 | Workstation | 71 |
66 | AI/ML | 66 |
100 | Energy Efficiency | 43 |
58 | Quick Comparison Final Score | 75 |
| Custom | Graphics Processor | AD103 |
| 5120 | Cores | 9728 |
| 320 / 160 | TMUs / ROPs | 304 / 112 |
| 7937.27 | Blender GPU | 8710.73 |
| — | Forza Horizon 5 | — |
| — | The Witcher 3 | — |
| — | Counter-Strike 2 | — |
| — | Far Cry 6 | — |
| — | Hogwarts Legacy | — |
| — | Call of Duty | — |
| — | Ghost of Tsushima | — |
| — | Cyberpunk 2077 | — |
| — | Tomb Raider | — |
| — | Average FPS | — |
| — | 1080p High | — |
| — | 1080p Ultra | — |
| — | 1440p Ultra | — |
| — | 4K Ultra | — |
| — | Margin of Error | — |
| 146407 | GB6 Compute Score | 217712 |
| 257 img/sec | Background Blur | 250.4 img/sec |
| 182.1 img/sec | Face Detection | 190 img/sec |
| 5.4 Gpixels/sec | Horizon Detection | 9.56 Gpixels/sec |
| 8.33 Gpixels/sec | Edge Detection | 12.8 Gpixels/sec |
| 8.86 Gpixels/sec | Gaussian Blur | 15.3 Gpixels/sec |
| 1.28 Gpixels/sec | Feature Matching | 1.97 Gpixels/sec |
| 455.4 Gpixels/sec | Stereo Matching | 1130 Gpixels/sec |
| 21658 FPS | Particle Physics | 28795.5 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 34430 |
| — | G2D Mark | 1250 |
| — | DirectX 11 | 313 FPS |
| — | DirectX 12 | 132 FPS |
| — | GPU Compute | 20406 Ops/s |
| 29452 | GB6 ML Single Precision | 36799 |
| 46343 | GB6 ML Half Precision | 53331 |
| 43305 | GB6 ML Quantized | 28104 |
| 10711 | Image Classification (SP) | 13466 |
| 42406 | Image Segmentation (HP) | 34767 |
| 42905 | Image Super Resolution (Q) | 42687 |
| 73489 | Face Detection (HP) | 70927 |
| 289766 | Pose Estimation (Q) | 239350 |
| 6087 | Text Classification (SP) | 3606 |
| 8881 | Machine Translation (HP) | 6519 |
| 10130 | Object Detection (SP) | 18153 |
| 84224 | Depth Estimation (Q) | 65667 |
| 264552 | Style Transfer (SP) | 414848 |
| Core ML | Framework | ONNX |
| GPU | Backend | DirectML |
| 259 GPixel/s | Pixel Fill Rate | 281 GPixel/s |
| 518 GTexel/s | Texture Fill Rate | 762 GTexel/s |
| 16.6 TFLOPS | FLOPS (FP32) | 48.7 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 16 GB |
| 9600 MHz | Memory Clock | 1400 MHz |
| — | Effective Memory Speed | 22400 Mbps |
| 512-bit | Bus | 256-bit |
| No | ECC | No |
| 614 GB/s | Memory Bandwidth | 716.8 GB/s |
| Custom | Interface | PCIe 4.0 x16 |
| — | 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 |
| March 3, 2026 | Released | September 20, 2022 |
| Laptop | Case | Desktop |
| Professional | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Apple M GPU | Architecture | Ada Lovelace |
| Custom | GPU Codename | AD103 |
| -Apple M5 Max (40-сore GPU)or above | Recommended CPU | -Intel Core i7 14700Kor above |
| 17913 | Steel Nomad Lite Score | 30172 |
| — | Time Spy | 28161 |
| 79412 | Solar Bay | 136931 |
| — | Port Royal | 17982 |
| — | Fire Strike | 64633 |
| 42244 | Wild Life Extreme | 59111 |
| — | Night Raid | 184963 |
| — | Base Clock | 2205 MHz |
| 1620 MHz | Boost Clock | 2505 MHz |
| 5120 | Shading Units | 9728 |
| 320 | Texture Mapping Units (TMUs) | 304 |
| 160 | Render Output Units (ROPs) | 112 |
| 640 | Compute Units (Pipelines) | 76 |
| — | Tensor Cores | 304 |
| — | Ray-tracing Cores | 76 |
| — | L1 Cache | 128KB per cluster |
| — | L2 Cache | 64MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare Apple M5 Max with another →