Key Differences
Advantages of GeForce RTX 4070 SUPER
Advantages of Apple M4 Pro GPU (20-core)
Specifications
Performance
| TGP | 220 W | 26 W |
Storage Details
| Bus | 192-bit | 192-bit |
Ports
| DisplayPort | 1.4a | - |
Other
| Forza Horizon 5 | 18313111992 | - |
| The Witcher 3 | 20517812969 | - |
| Counter-Strike 2 | 28620815584 | - |
| Far Cry 6 | 15414212577 | - |
| Hogwarts Legacy | 1341088846 | - |
| CoD: Modern Warfare III | 17515912481 | - |
| Ghost of Tsushima | 1191018351 | - |
| Cyberpunk 2077 | 1481368942 | - |
| Shadow of the Tomb Raider | 24322217393 | - |
| 1080p High | 183 | - |
| 1080p Ultra | 154 | - |
| 1440p Ultra | 121 | - |
| 4K Ultra | 71 | - |
| Margin of Error | Low | High |
| Time Spy | 20886 | - |
| Solar Bay | 98132 | - |
| Port Royal | 13122 | - |
| Fire Strike | 50125 | - |
| Wild Life Extreme | 41653 | 19428 |
| Night Raid | 164996 | - |
| Background Blur | 359.5 img/sec | 125.1 img/sec |
| Face Detection | 210 img/sec | 80 img/sec |
| Horizon Detection | 7.61 Gpixels/sec | 2.88 Gpixels/sec |
| Edge Detection | 10.4 Gpixels/sec | 4.22 Gpixels/sec |
| Gaussian Blur | 11.3 Gpixels/sec | 2.98 Gpixels/sec |
| Feature Matching | 1.97 Gpixels/sec | 0.8 Gpixels/sec |
| Stereo Matching | 969.3 Gpixels/sec | 235 Gpixels/sec |
| Particle Physics | 29061.4 FPS | 9516.1 FPS |
| API | OpenGL | Metal |
| G2D Mark | 1189 | - |
| DirectX 11 | 272 FPS | - |
| DirectX 12 | 110 FPS | - |
| GPU Compute | 17043 Ops/s | - |
| Aztec Ruins Normal Tier | 1132.4 FPS | 757.5 FPS |
| Car Chase | 981.8 FPS | 576.2 FPS |
| Manhattan 3.1.1 (1440p) | 840.6 FPS | 473.2 FPS |
| T-Rex | 4325.3 FPS | 2148.5 FPS |
| Tessellation | 7090.8 FPS | - |
| ALU 2 | 6890.2 FPS | 912.2 FPS |
| Driver Overhead 2 | 290.1 FPS | 535.8 FPS |
| OS | Windows | OS X |
| Image Classification (SP) | 12146 | 8046 |
| Image Segmentation (HP) | 23932 | 15443 |
| Image Super Resolution (Q) | 36321 | 20807 |
| Face Detection (HP) | 52836 | 30860 |
| Pose Estimation (Q) | 179788 | 56783 |
| Text Classification (SP) | 3371 | 2888 |
| Machine Translation (HP) | 5017 | 6167 |
| Object Detection (SP) | 15164 | 7592 |
| Depth Estimation (Q) | 62500 | 33607 |
| Style Transfer (SP) | 357489 | 126726 |
| Framework | ONNX | Core ML |
| Backend | DirectML | GPU |
| Vendor | Nvidia | Apple |
| Build | Discrete | Integrated |
| Released | January 17, 2024 | October 29, 2024 |
| Launch price (MSRP) | $599 | - |
| Case | Desktop | Laptop |
| Purpose | Gaming | Professional |
| Segment | Mid-range | Mid-range |
| Architecture | Ada Lovelace | Apple M GPU |
| GPU Codename | AD104 | Custom |
| Rival Equivalent | Radeon RX 7900 XT | GeForce RTX 4060 Laptop |
| Base Clock | 1980 MHz | 500 MHz |
| Boost Clock | 2475 MHz | 1800 MHz |
| Shading Units | 7168 | 2560 |
| Texture Mapping Units (TMUs) | 224 | 160 |
| Render Output Units (ROPs) | 80 | 80 |
| Compute Units (Pipelines) | 56 | 320 |
| Tensor Cores | 224 | - |
| Ray-tracing Cores | 56 | - |
| L1 Cache | 128KB per cluster | - |
| L2 Cache | 48MB shared | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
| Pixel Fill Rate | 198 GPixel/s | 144 GPixel/s |
| Texture Fill Rate | 554 GTexel/s | 288 GTexel/s |
| Interface | PCIe 4.0 x16 | Custom |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 3 nm |
| Die Size | 294 mm² | - |
| Transistor Count | 35 billion | - |
| Transistor Density | 119.05 MTr/mm² | - |
| Memory Type | GDDR6X | System Shared |
| Memory Size | 12 GB | - |
| Memory Clock | 1313 MHz | 8533 MHz |
| Effective Memory Speed | 21000 Mbps | 15000 Mbps |
| ECC | No | No |
| DirectX | 12 | - |
| Vulkan | 1.3 | - |
| OpenGL | 4.6 | - |
| OpenCL | 3.0 | - |
| CUDA | 8.9 | - |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 3 | No |
| Max. Temperature | - | 100°C |