Apple M4 Pro GPU (20-core) vs Nvidia GeForce RTX 3070 Laptop
40
out 100
VS
40
out 100
Compared 2 processors: Apple M4 Pro GPU (20-core), vs Nvidia GeForce RTX 3070 Laptop. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | n/a n/a n/a n/a | 123 79 68 45 |
 The Witcher 3 | n/a n/a n/a n/a | 141 112 83 46 |
 Counter-Strike 2 | n/a n/a n/a n/a | 201 153 112 54 |
 Far Cry 6 | n/a n/a n/a n/a | 106 92 76 39 |
 Hogwarts Legacy | n/a n/a n/a n/a | 76 63 46 25 |
 COD Modern Warfare 3 | n/a n/a n/a n/a | 96 86 60 40 |
 Ghost of Tsushima | n/a n/a n/a n/a | 71 59 44 25 |
 Cyberpunk 2077 | n/a n/a n/a n/a | 84 72 45 22 |
 Shadow of the Tomb Raider | n/a n/a n/a n/a | 125 115 83 45 |
| 1080p High | n/a | 114 |
| 1080p Ultra | n/a | 92 |
| 1440p Ultra | n/a | 69 |
| 4K Ultra | n/a | 38 |
| Deviation | n/a | Low |
Benchmarks
| Time Spy | n/a | 10479 |
| Solar Bay | n/a | 45677 |
| Port Royal | n/a | 6250 |
| Fire Strike | n/a | 26767 |
| Night Raid | n/a | 83274 |
| Background Blur | 125.1 frames/s | 170.3 frames/s |
| Face Detection | 80 frames/s | 113.6 frames/s |
| Horizon Detection | 2.88 Gpix/sec | 5.59 Gpix/sec |
| Edge Detection | 4.22 Gpix/sec | 7.94 Gpix/sec |
| Gaussian Blur | 2.98 Gpix/sec | 6.19 Gpix/sec |
| Feature Matching | 0.8 Gpix/sec | 1.16 Gpix/sec |
| Stereo Matching | 235 Gpix/sec | 467 Gpix/sec |
| Particle Physics | 9516.1 fps | 15131.3 fps |
| API | OpenCL | OpenCL |
| G2D Mark | n/a | 644 |
| DirectX 11 | n/a | 138 fps |
| DirectX 12 | n/a | 64 fps |
| GPU Compute | n/a | 6902 Ops/s |
| Aztec Ruins (Normal) | 757.5 fps | 644.4 fps |
| Car Chase | 576.2 fps | 565.3 fps |
| Manhattan 3.1.1 (1440p) | 473.2 fps | 483.8 fps |
| T-Rex | 2148.5 fps | 2380.5 fps |
| ALU 2 | 912.2 fps | 3169.7 fps |
| Driver Overhead 2 | 535.8 fps | 246.7 fps |
| API | Metal | OpenGL |
| OS | OS X | Windows |
| Tessellation | n/a | 3511.5 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Apple | Nvidia |
| Build | Integrated | Discrete |
| Announced | October, 29, 2024 | January, 12, 2021 |
| Form Factor | Laptop use | Laptop use |
| Use case | Professional | Gaming |
| Segment | Mid-range | High-end |
| Architecture | Apple M GPU | Ampere |
| Codename | Custom | GA104 (GN20-E5) |
GPU
| GPU Frequency | 500 MHz | 780-1215 MHz |
| Boost GPU Frequency | 1800 MHz | 1290-1620 MHz |
| Shader Units | 2560 | 5120 |
| TMUs | 160 | 160 |
| ROPs | 80 | 80 |
| Execution Units | 320 | 40 |
| Ray Tracing Cores | n/a | 40 |
| Tensor Cores | n/a | 160 |
| L1 cache | n/a | 128 KB/core |
| L2 cache | n/a | 4000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 144 Gpix/sec | 103-130 Gpix/sec |
| Texture Fill Rate | 288 GTex/s | 206-259 GTex/s |
| FLOPS | 9.2 TFLOPS | 13.2-16.6 TFLOPS |
Process
| Interface | Custom | PCIe 4.0 x16 |
| TGP | 32 W | 80-150 W |
| Process | TSMC | Samsung |
| Process tech. | 3 nm | 8 nm |
| Max temperature | 100 °C | n/a |
| Transistor Size | n/a | 392 mm² |
| Transistor count | n/a | 17.4 billion |
| Transistor density | n/a | 44.39 MTr/mm² |
Memory
| Interface | System Shared | GDDR6 |
| Memory Frequency | 7500 MHz | 1500-1750 MHz |
| Bus | 192 bit | 256 bit |
| ECC support | No | No |
| Effective Memory Speed | 15000 MB/s | 12000-14000 MB/s |
| Memory Size | n/a | 8 GB |
Max Throughput
API
| DirectX | n/a | 12 |
| Vulkan | n/a | 1.2 |
| OpenGL | n/a | 4.6 |
| CUDA | n/a | 8.6 |
| DisplayPort | n/a | 1.4a |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 2 |
Results
No clear favorite identified yet; updates may follow as new data arrives.
Survey
Total Votes: 0
