Apple M4 Max GPU (40-core) vs M3 Max GPU (40-core)
We compared two integrated laptop professional GPUs: the Apple M4 Max GPU (40-core) with 640 pipelines and 5120 shaders against the 1 year and 1 month older M3 Max GPU (40-core) that utilizes 640 pipelines and 5120 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Key differences
Reasons to consider the Apple M4 Max GPU (40-core)
- Performs slightly better (up to 17%) in 3DMark Steel Nomad Lite
- 15% higher maximum theoretical performance (16.2 vs 14.1 TFLOPS)
- Has 33% higher memory bandwidth: 546 vs 409.6 GB/s
- Achieves 24% more points in the GeekBench 6 Compute test (116K vs 94K)
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Solar Bay | 61312 | 49656 |
| Wild Life Extreme | 36641 | 30893 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 195 img/sec | 157.6 img/sec |
| Face Detection | 125.9 img/sec | 100.9 img/sec |
| Horizon Detection | 4.82 Gpixels/sec | 3.99 Gpixels/sec |
| Edge Detection | 7.47 Gpixels/sec | 6.04 Gpixels/sec |
| Gaussian Blur | 5.8 Gpixels/sec | 5 Gpixels/sec |
| Feature Matching | 1.06 Gpixels/sec | 0.84 Gpixels/sec |
| Stereo Matching | 417.4 Gpixels/sec | 363.8 Gpixels/sec |
| Particle Physics | 17079.9 FPS | 12226.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Blender
Blender GPU
Recent User Tests
Apple M4 Max GPU (40-core)
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-07-10 (thomas) | Geekbench 6 OpenCL | 116478 |
Apple M3 Max GPU (40-core)
No benchmark results yet
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 10302 | 8685 |
| Image Segmentation (HP) | 23763 | 20739 |
| Image Super Resolution (Q) | 29314 | 22775 |
| Face Detection (HP) | 42016 | 37676 |
| Pose Estimation (Q) | 105972 | 91609 |
| Text Classification (SP) | 2963 | 2909 |
| Machine Translation (HP) | 6594 | 5274 |
| Object Detection (SP) | 8935 | 7480 |
| Depth Estimation (Q) | 43143 | 38212 |
| Style Transfer (SP) | 221563 | 190681 |
| Framework | Core ML | Core ML |
| Backend | GPU | GPU |
Specifications
Technical specifications of Apple M4 Max GPU (40-core) and M3 Max GPU (40-core)General
| Vendor | Apple | Apple |
| Build | Integrated | Integrated |
| Released | October 30, 2024 | October 31, 2023 |
| Case | Laptop | Laptop |
| Purpose | Professional | Professional |
| Segment | Mid-range | High-end |
| Architecture | Apple M GPU | Apple M GPU |
| GPU Codename | Custom | - |
| Rival Equivalent | - GeForce RTX 4070 Laptop | - GeForce RTX 4070 Laptop |
| Successor | - Apple M5 Max GPU (40-core) | - Apple M5 Max GPU (40-core) |
| Recommended CPU | - Apple M4 Max (16-Core) or above | - Apple M3 Max or above |
| Used in CPUs | - Apple M4 Max (16-Core) | - Apple M3 Max |
Laptop GPU ranking (14th and 21st place)
Graphics Processing Unit
| Base Clock | 500 MHz | 500 MHz |
| Boost Clock | 1578 MHz | 1380 MHz |
| Shading Units | 5120 | 5120 |
| Texture Mapping Units (TMUs) | 320 | 320 |
| Render Output Units (ROPs) | 160 | 160 |
| Compute Units (Pipelines) | 640 | 640 |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 252 GPixel/s | 221 GPixel/s |
| Texture Fill Rate | 505 GTexel/s | 442 GTexel/s |
FLOPS (FP32)
Physical
| Interface | Custom | Custom |
| TGP | 50 W | 60 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 3 nm | 3 nm |
| Transistor Count | - | 56 billion |
| Max. Temperature | 100°C | 100°C |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | 8533 MHz | 6400 MHz |
| Effective Memory Speed | - | 12800 Mbps |
| Bus | 512-bit | 512-bit |
| ECC | No | No |
Memory Bandwidth
API
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
Cast your vote
Total votes: 51