Apple M5 Ultra GPU (64-core) vs Max GPU (32-core)
VS
Apple M5 Ultra GPU (64-core)
Custom
Apple M5 Max GPU (32-core)
Custom
We performed a head-to-head comparison of the Apple M5 Ultra GPU (64-core) with 1024 pipelines and 8192 shaders against the 6 months older Max GPU (32-core) that utilizes 512 pipelines and 4096 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
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Scores marked with a red asterisk (**) represent initial estimates from early testing.
The "Energy Efficiency" metric has less impact on the NanoReview Score for desktop GPU.
Key differences
Reasons to consider the Apple M5 Ultra GPU (64-core)
- 2x higher maximum theoretical performance (26.5 vs 13.3 TFLOPS)
- Has 2.7x higher memory bandwidth: 1228.8 vs 460.8 GB/s
- Has 2x more shading units (8192 vs 4096)
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Solar Bay | - | 69788 |
| Wild Life Extreme | - | 35786 |
GeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | - | 234.8 img/sec |
| Face Detection | - | 158.1 img/sec |
| Horizon Detection | - | 4.48 Gpixels/sec |
| Edge Detection | - | 6.62 Gpixels/sec |
| Gaussian Blur | - | 7.19 Gpixels/sec |
| Feature Matching | - | 1.17 Gpixels/sec |
| Stereo Matching | - | 384.9 Gpixels/sec |
| Particle Physics | - | 17866.8 FPS |
| API | - | OpenCL |
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) | - | 10338 |
| Image Segmentation (HP) | - | 42053 |
| Image Super Resolution (Q) | - | 41729 |
| Face Detection (HP) | - | 71929 |
| Pose Estimation (Q) | - | 287035 |
| Text Classification (SP) | - | 2958 |
| Machine Translation (HP) | - | 9156 |
| Object Detection (SP) | - | 9951 |
| Depth Estimation (Q) | - | 82338 |
| Style Transfer (SP) | - | 264780 |
| Framework | - | Core ML |
| Backend | - | GPU |
Specifications
Technical specifications of Apple M5 Ultra GPU (64-core) and Max GPU (32-core)General
| Vendor | Apple | Apple |
| Build | Integrated | Integrated |
| Released | August 25, 2026 | March 3, 2026 |
| Case | Desktop | Laptop |
| Purpose | Professional | Professional |
| Segment | High-end | Mid-range |
| Architecture | Apple M GPU | Apple M GPU |
| GPU Codename | Custom | Custom |
| Rival Equivalent | - GeForce RTX 5080 | - |
| Recommended CPU | - Apple M5 Ultra (30-Core) or above | - Apple M5 Max (32-сore GPU) or above |
| Used in CPUs | - Apple M5 Ultra (30-Core) | - Apple M5 Max (32-сore GPU) |
Desktop GPU rating (#22nd place)
Laptop GPU ranking (#9th place)
Graphics Processing Unit
| Base Clock | 500 MHz | - |
| Boost Clock | 1620 MHz | 1620 MHz |
| Shading Units | 8192 | 4096 |
| Texture Mapping Units (TMUs) | 640 | 256 |
| Render Output Units (ROPs) | 320 | 128 |
| Compute Units (Pipelines) | 1024 | 512 |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 518 GPixel/s | 207 GPixel/s |
| Texture Fill Rate | 1037 GTexel/s | 415 GTexel/s |
FLOPS (FP32)
Physical
| Interface | Custom | Custom |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 3 nm | 3 nm |
| Transistor Count | - | 28 billion |
| Max. Temperature | - | 100°C |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | 9600 MHz | 9600 MHz |
| Bus | 1024-bit | 384-bit |
| ECC | No | No |
Memory Bandwidth
API
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
Cast your vote
Total votes: < 1