Nvidia GeForce RTX 5090 vs Apple M4 Max GPU (40-core)
97
out 100
VS
50
out 100
Compared 2 processors: Nvidia GeForce RTX 5090, vs Apple M4 Max GPU (40-core). 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 | 332 242 231 183 | 0 0 0 0 |
 The Witcher 3 | 366 338 234 127 | 157 107 78 61 |
 Counter-Strike 2 | 379 271 209 98 | 0 0 0 0 |
 Far Cry 6 | 235 202 198 124 | 0 0 0 0 |
 Hogwarts Legacy | 244 210 167 96 | 0 0 0 0 |
 COD Modern Warfare 3 | 337 333 269 184 | 0 0 0 0 |
 Ghost of Tsushima | 221 190 170 114 | 0 0 0 0 |
 Cyberpunk 2077 | 259 231 166 77 | 0 0 0 0 |
 Shadow of the Tomb Raider | 334 306 238 128 | 0 0 0 0 |
| 1080p High | 301 | - |
| 1080p Ultra | 258 | - |
| 1440p Ultra | 209 | - |
| 4K Ultra | 126 | - |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 47515 | n/a |
| Solar Bay | 213229 | 31561 |
| Port Royal | 37529 | n/a |
| Fire Strike | 90200 | n/a |
| Night Raid | 209016 | n/a |
| Background Blur | 333 frames/s | 195 frames/s |
| Face Detection | 298.5 frames/s | 125.9 frames/s |
| Horizon Detection | 21.7 Gpix/sec | 4.82 Gpix/sec |
| Edge Detection | 33.7 Gpix/sec | 7.47 Gpix/sec |
| Gaussian Blur | 34.5 Gpix/sec | 5.8 Gpix/sec |
| Feature Matching | 2.53 Gpix/sec | 1.06 Gpix/sec |
| Stereo Matching | 2850 Gpix/sec | 417.4 Gpix/sec |
| Particle Physics | 59146.9 fps | 17079.9 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1444 | n/a |
| DirectX 11 | 344 fps | n/a |
| DirectX 12 | 195 fps | n/a |
| GPU Compute | 28243 Ops/s | n/a |
| Aztec Ruins (Normal) | 1397.2 fps | 1316.3 fps |
| Car Chase | 1150.3 fps | 950.9 fps |
| Manhattan 3.1.1 (1440p) | 1178.2 fps | 911 fps |
| T-Rex | 4812.3 fps | 3917.4 fps |
| ALU 2 | 5992.8 fps | 1756 fps |
| Driver Overhead 2 | 269.7 fps | 654.4 fps |
| API | OpenGL | Metal |
| OS | Windows | OS X |
| Tessellation | 5991.7 | n/a |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | Nvidia | Apple |
| Build | Discrete | Integrated |
| Announced | January, 7, 2025 | October, 30, 2024 |
| Form Factor | PC use | Laptop use |
| Use case | Gaming | Professional |
| Segment | High-end | Mid-range |
| Architecture | Blackwell 2.0 | Apple M GPU |
| Codename | GB202-300-A1 | Custom |
| Price | 1999 | n/a |
GPU
| GPU Frequency | 2017 MHz | 500 MHz |
| Boost GPU Frequency | 2407 MHz | 1800 MHz |
| Shader Units | 21760 | 5120 |
| TMUs | 680 | 320 |
| ROPs | 176 | 160 |
| Execution Units | 170 | 640 |
| Ray Tracing Cores | 170 | n/a |
| Tensor Cores | 680 | n/a |
| L1 cache | 128 KB/core | n/a |
| L2 cache | 88 KB/core | n/a |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 424 Gpix/sec | 288 Gpix/sec |
| Texture Fill Rate | 1637 GTex/s | 576 GTex/s |
| FLOPS | 104.8 TFLOPS | 18.4 TFLOPS |
Process
| Interface | PCIe 5.0 x16 | Custom |
| TGP | 575 W | 62 W |
| Process | TSMC | TSMC |
| Process tech. | 4 nm | 3 nm |
| Max temperature | n/a | 100 °C |
| Transistor Size | 750 mm² | n/a |
| Transistor count | 92.2 billion | n/a |
| Transistor density | 122.93 MTr/mm² | n/a |
Memory
| Interface | GDDR7 | System Shared |
| Memory Frequency | 1750 MHz | 8533 MHz |
| Bus | 512 bit | 512 bit |
| ECC support | No | No |
| Effective Memory Speed | 28000 MB/s | n/a |
| Memory Size | 32 GB | n/a |
Max Throughput
API
| DirectX | 12 | n/a |
| Vulkan | 1.4 | n/a |
| OpenGL | 4.6 | n/a |
| CUDA | 10.1 | n/a |
| DisplayPort | 2.1a | n/a |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | No |
Results
After analyzing the data, we consider Nvidia GeForce RTX 5090 the clear winner in this comparison.
Survey
Total Votes: 0
