Apple M5 GPU (10-Core) vs M2 GPU (8-core)
VS
We compared two integrated laptop professional GPUs: the Apple M5 GPU (10-Core) with 160 pipelines and 1280 shaders against the 3 years and 4 months older M2 GPU (8-core) that utilizes 128 pipelines and 1024 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 M5 GPU (10-Core)
- Performs significantly better (up to 2.3x) in 3DMark Steel Nomad Lite
- Manufactured using a more efficient 3 nm process technology
- 41% higher maximum theoretical performance (4.1 vs 2.9 TFLOPS)
- Achieves 2.6x more points in the GeekBench 6 Compute test (75K vs 29K)
- Has 49% higher memory bandwidth: 153 vs 102.4 GB/s
- Has 25% more shading units (1280 vs 1024)
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Solar Bay | 24536 | 7316 |
| Wild Life Extreme | 12278 | 5676 |
GeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | 155.7 img/sec | 58.7 img/sec |
| Face Detection | 178.1 img/sec | 35.2 img/sec |
| Horizon Detection | 2.22 Gpixels/sec | 1.1 Gpixels/sec |
| Edge Detection | 2.87 Gpixels/sec | 1.82 Gpixels/sec |
| Gaussian Blur | 5.8 Gpixels/sec | 1.2 Gpixels/sec |
| Feature Matching | 0.95 Gpixels/sec | 0.37 Gpixels/sec |
| Stereo Matching | 190.7 Gpixels/sec | 96 Gpixels/sec |
| Particle Physics | 6579.1 FPS | 3825.9 FPS |
| API | Metal | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Blender
Blender GPU
Recent User Tests
Apple M5 GPU (10-Core)
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-01-03 -> Rennsport | Geekbench 6 OpenCL | 48688 |
Apple M2 GPU (8-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) | 6348 | 3242 |
| Image Segmentation (HP) | 16813 | 4890 |
| Image Super Resolution (Q) | 30322 | 7149 |
| Face Detection (HP) | 34387 | 10340 |
| Pose Estimation (Q) | 111591 | 21268 |
| Text Classification (SP) | 2319 | 2268 |
| Machine Translation (HP) | 5555 | 1122 |
| Object Detection (SP) | 6450 | 3007 |
| Depth Estimation (Q) | 53195 | 13941 |
| Style Transfer (SP) | 82314 | 35943 |
| Framework | Core ML | Core ML |
| Backend | GPU | GPU |
Specifications
Technical specifications of Apple M5 GPU (10-Core) and M2 GPU (8-core)General
| Vendor | Apple | Apple |
| Build | Integrated | Integrated |
| Released | October 15, 2025 | June 6, 2022 |
| Case | Laptop | Laptop |
| Purpose | Professional | Professional |
| Segment | Mid-range | Mid-range |
| Architecture | Apple M GPU | Apple M GPU |
| GPU Codename | Custom | - |
| Rival Equivalent | - Adreno X2-90 | - |
| Successor | - | - Apple M5 GPU (10-Core) |
| Recommended CPU | - Apple M5 (10-Core) or above | - Apple M2 or above |
| Used in CPUs | - Apple M5 (10-Core) | - Apple M2 |
Laptop GPU ranking (44th and 89th place)
Graphics Processing Unit
| Base Clock | - | 500 MHz |
| Boost Clock | 1620 MHz | 1398 MHz |
| Shading Units | 1280 | 1024 |
| Texture Mapping Units (TMUs) | 80 | 64 |
| Render Output Units (ROPs) | 40 | 32 |
| Compute Units (Pipelines) | 160 | 128 |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 65 GPixel/s | 45 GPixel/s |
| Texture Fill Rate | 130 GTexel/s | 89 GTexel/s |
FLOPS (FP32)
Physical
| Interface | Custom | Custom |
| TGP | - | 15 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 3 nm | 5 nm |
| Transistor Count | 28 billion | 11.6 billion |
| Max. Temperature | 100°C | 94°C |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | 9600 MHz | 6400 MHz |
| Effective Memory Speed | - | 12800 Mbps |
| Bus | 128-bit | 128-bit |
| ECC | No | No |
Memory Bandwidth
API
| Ray Tracing | Yes | No |
| DLSS | No | No |
Cast your vote
Total votes: 7