Intel Arc iGPU (4-Cores) vs Apple M5 Ultra GPU (80-core)
We performed a head-to-head comparison of the Intel Arc iGPU (4-Cores) with 64 pipelines and 512 shaders against the 2 years and 9 months newer Apple M5 Ultra GPU (80-core) that utilizes 1280 pipelines and 10240 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Please note that the tests on the Apple M5 Ultra GPU (80-core) are done on an engineering sample provided by our insiders. The data will be more accurate after the final version of this GPU is available.
Key differences
Reasons to consider the Apple M5 Ultra GPU (80-core)
- 16.6x higher maximum theoretical performance (33.2 vs 2 TFLOPS)
- Manufactured using a more efficient 3 nm process technology
- Has 20x more shading units (10240 vs 512)
Benchmarks
Graphics cards’ performance in recent benchmarking appsGeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | 37.6 img/sec | - |
| Face Detection | 17.2 img/sec | - |
| Horizon Detection | 0.3 Gpixels/sec | - |
| Edge Detection | 0.63 Gpixels/sec | - |
| Gaussian Blur | 0.94 Gpixels/sec | - |
| Feature Matching | 0.22 Gpixels/sec | - |
| Stereo Matching | 60 Gpixels/sec | - |
| Particle Physics | 3695.9 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) | 2902 | - |
| Image Segmentation (HP) | 5473 | - |
| Image Super Resolution (Q) | 2967 | - |
| Face Detection (HP) | 6068 | - |
| Pose Estimation (Q) | 8220 | - |
| Text Classification (SP) | 609 | - |
| Machine Translation (HP) | 1146 | - |
| Object Detection (SP) | 2766 | - |
| Depth Estimation (Q) | 6405 | - |
| Style Transfer (SP) | 26796 | - |
| Framework | ONNX | - |
| Backend | DirectML | - |
Specifications
Technical specifications of Intel Arc iGPU (4-Cores) and Apple M5 Ultra GPU (80-core)General
| Vendor | Intel | Apple |
| Build | Integrated | Integrated |
| Released | December 14, 2023 | August 25, 2026 |
| Case | Laptop | Desktop |
| Purpose | Generic | Professional |
| Segment | Mid-range | High-end |
| Architecture | Xe LPG | Apple M GPU |
| GPU Codename | - | Custom |
| Rival Equivalent | - Radeon 740M | - GeForce RTX 5080 |
| Recommended CPU | - Intel Core Ultra 5 125U or above | - Apple M5 Ultra (36-Core) or above |
| Used in CPUs | - Intel Core Ultra 7 251HX - Intel Core Ultra 7 270HX Plus - Intel Core Ultra 9 290HX Plus - Intel Core Ultra 7 270K Plus - Intel Core Ultra 5 250K Plus - Intel Core Ultra 5 225U - Intel Core Ultra 5 235U - Intel Core Ultra 7 255U - and 12 more |
- Apple M5 Ultra (36-Core) |
Laptop GPU ranking (#96th place)
Graphics Processing Unit
| Base Clock | 300 MHz | 500 MHz |
| Boost Clock | 1750-2000 MHz (configurable) | 1620 MHz |
| Shading Units | 512 | 10240 |
| Texture Mapping Units (TMUs) | 32 | 640 |
| Render Output Units (ROPs) | 16 | 320 |
| Compute Units (Pipelines) | 64 | 1280 |
| Ray-tracing Cores | 4 | - |
| L1 Cache | 768KB shared | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 28-32 GPixel/s | 518 GPixel/s |
| Texture Fill Rate | 56-64 GTexel/s | 1037 GTexel/s |
FLOPS (FP32)
Physical
| Interface | Ring Bus | Custom |
| TGP | 14 W | - |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 3 nm |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | - | 9600 MHz |
| Bus | - | 1024-bit |
| ECC | - | No |
Memory Bandwidth
API
| DirectX | 12 | - |
| Vulkan | 1.3 | - |
| OpenGL | 4.6 | - |
| OpenCL | 3.0 | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1 | - |
Cast your vote
Total votes: < 1