AMD Radeon 890M vs Apple M3 Pro GPU (18-core)
VS
AMD Radeon 890M
Strix Point
Apple M3 Pro GPU (18-core)
Custom
We compared two integrated laptop graphics cards: the Radeon 890M with 16 pipelines and 1024 shaders against the 7 months older Apple M3 Pro GPU (18-core) that utilizes 288 pipelines and 2304 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 M3 Pro GPU (18-core)
- Performs significantly better (up to 92%) in 3DMark Steel Nomad Lite
- Manufactured using a more efficient 3 nm process technology
- Has 2.3x more shading units (2304 vs 1024)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 57 30 25 14 |
- |
| The Witcher 3 | 36 32 18 - |
- |
| Counter-Strike 2 | 51 34 25 10 |
- |
| Far Cry 6 | 43 37 23 13 |
- |
| Hogwarts Legacy | 25 17 14 - |
- |
| CoD: Modern Warfare III | 39 34 22 14 |
- |
| Ghost of Tsushima | 25 17 12 - |
- |
| Cyberpunk 2077 | 23 23 12 - |
- |
| Shadow of the Tomb Raider | 43 34 21 10 |
- |
| 1080p High | 38 | - |
| 1080p Ultra | 29 | - |
| 1440p Ultra | 19 | - |
| 4K Ultra | 10 | - |
| Margin of Error | Low | Medium |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 3305 | - |
| Solar Bay | 15412 | 22637 |
| Port Royal | 1795 | - |
| Fire Strike | 8908 | - |
| Wild Life Extreme | 6884 | 14021 |
| Night Raid | 37640 | - |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 98.6 img/sec | 82.1 img/sec |
| Face Detection | 42 img/sec | 53.6 img/sec |
| Horizon Detection | 1.25 Gpixels/sec | 1.82 Gpixels/sec |
| Edge Detection | 1.6 Gpixels/sec | 2.59 Gpixels/sec |
| Gaussian Blur | 1.69 Gpixels/sec | 1.84 Gpixels/sec |
| Feature Matching | 0.55 Gpixels/sec | 0.48 Gpixels/sec |
| Stereo Matching | 214.8 Gpixels/sec | 148.6 Gpixels/sec |
| Particle Physics | 7757.7 FPS | 4893.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 979 | - |
| DirectX 11 | 73 FPS | - |
| DirectX 12 | 37 FPS | - |
| GPU Compute | 4162 Ops/s | - |
Blender
Blender GPU
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) | 3563 | 5578 |
| Image Segmentation (HP) | 6170 | 9924 |
| Image Super Resolution (Q) | 10762 | 13323 |
| Face Detection (HP) | 13773 | 19900 |
| Pose Estimation (Q) | 37861 | 35730 |
| Text Classification (SP) | 2572 | 2904 |
| Machine Translation (HP) | 4699 | 4985 |
| Object Detection (SP) | 2845 | 5496 |
| Depth Estimation (Q) | 17260 | 23344 |
| Style Transfer (SP) | 86751 | 78342 |
| Framework | ONNX | Core ML |
| Backend | DirectML | GPU |
Results were compared using different ML frameworks
Specifications
Technical specifications of Radeon 890M and Apple M3 Pro GPU (18-core)General
| Vendor | Amd | Apple |
| Build | Integrated | Integrated |
| Released | June 3, 2024 | October 31, 2023 |
| Case | Laptop | Laptop |
| Purpose | Generic | Professional |
| Segment | Mid-range | Mid-range |
| Architecture | RDNA 3.5 | Apple M GPU |
| GPU Codename | Strix Point | Custom |
| Rival Equivalent | - Intel Arc 140V | - GeForce RTX 4060 Laptop |
| Successor | - Radeon 8060S | - Apple M5 Pro GPU (20-core) |
| Recommended CPU | - AMD Ryzen AI 9 HX 370 or above | - Apple M3 Pro or above |
| Used in CPUs | - AMD Ryzen AI 9 HX 470 - AMD Ryzen AI 9 HX 475 - AMD Ryzen Z2 Extreme - AMD Ryzen AI 9 HX 375 - AMD Ryzen AI 9 HX 370 |
- Apple M3 Pro |
Laptop GPU ranking (78th and 60th place)
Graphics Processing Unit
| Base Clock | 400 MHz | 500 MHz |
| Boost Clock | 2900 MHz | 1380 MHz |
| Shading Units | 1024 | 2304 |
| Texture Mapping Units (TMUs) | 64 | 144 |
| Render Output Units (ROPs) | 32 | 72 |
| Compute Units (Pipelines) | 16 | 288 |
| Tensor Cores | No | - |
| Ray-tracing Cores | 16 | - |
| L1 Cache | 128KB per cluster | - |
| L2 Cache | 2MB shared | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 93 GPixel/s | 99 GPixel/s |
| Texture Fill Rate | 186 GTexel/s | 199 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | Custom |
| TGP | 15 W | 30 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 3 nm |
| Die Size | 233 mm² | - |
| Transistor Count | 34 billion | 25.2 billion |
| Transistor Density | 145.92 MTr/mm² | - |
| Max. Temperature | 100°C | 100°C |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | - | 6400 MHz |
| Effective Memory Speed | - | 12800 Mbps |
| Bus | - | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | - |
| Vulkan | 1.4 | - |
| OpenGL | 4.6 | - |
| OpenCL | 2.1 | - |
| CUDA | None | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1 | - |
Cast your vote
Total votes: 14