Apple M3 Pro GPU (18-core) vs Adreno X1-85
Apple M3 Pro GPU (18-core)
Custom
Adreno X1-85
Adreno X1
We compared two integrated laptop graphics cards: the Apple M3 Pro GPU (18-core) with 288 pipelines and 2304 shaders against the Adreno X1-85 that utilizes 6 pipelines and 1536 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Some GPUs come in different configurations. For greater precision, pick a specific config below
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 3x) in 3DMark Steel Nomad Lite
- 39% higher maximum theoretical performance (6.4 vs 4.6 TFLOPS)
- Manufactured using a more efficient 3 nm process technology
- Achieves 77% more points in the GeekBench 6 Compute test (43K vs 24K)
- Has 50% more shading units (2304 vs 1536)
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | - | 1695 |
| Solar Bay | 22637 | 10596 |
| Fire Strike | - | 6134 |
| Wild Life Extreme | 14021 | 6152 |
| Night Raid | - | 28868 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 82.1 img/sec | 36.4 img/sec |
| Face Detection | 53.6 img/sec | 17.3 img/sec |
| Horizon Detection | 1.82 Gpixels/sec | 1.19 Gpixels/sec |
| Edge Detection | 2.59 Gpixels/sec | 1.3 Gpixels/sec |
| Gaussian Blur | 1.84 Gpixels/sec | 1.42 Gpixels/sec |
| Feature Matching | 0.48 Gpixels/sec | 0.3 Gpixels/sec |
| Stereo Matching | 148.6 Gpixels/sec | 72.4 Gpixels/sec |
| Particle Physics | 4893.9 FPS | 4692.5 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | - | 518 |
| DirectX 11 | - | 19 FPS |
| DirectX 12 | - | 10 FPS |
| GPU Compute | - | 1958 Ops/s |
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) | 5578 | 1347 |
| Image Segmentation (HP) | 9924 | 2661 |
| Image Super Resolution (Q) | 13323 | 3084 |
| Face Detection (HP) | 19900 | 5354 |
| Pose Estimation (Q) | 35730 | 7719 |
| Text Classification (SP) | 2904 | 292 |
| Machine Translation (HP) | 4985 | 1108 |
| Object Detection (SP) | 5496 | 660 |
| Depth Estimation (Q) | 23344 | 3876 |
| Style Transfer (SP) | 78342 | 12048 |
| Framework | Core ML | ONNX |
| Backend | GPU | DirectML |
Results were compared using different ML frameworks
Specifications
Technical specifications of Apple M3 Pro GPU (18-core) and Adreno X1-85General
| Vendor | Apple | Qualcomm |
| Build | Integrated | Integrated |
| Released | October 31, 2023 | October 24, 2023 |
| Case | Laptop | Laptop |
| Purpose | Professional | Generic |
| Segment | Mid-range | Entry-level |
| Architecture | Apple M GPU | Adreno X1 |
| GPU Codename | Custom | Adreno X1 |
| Rival Equivalent | - GeForce RTX 4060 Laptop | - Apple M4 GPU (10-Core) |
| Successor | - Apple M5 Pro GPU (20-core) | - Adreno X2-90 |
| Recommended CPU | - Apple M3 Pro or above | - Qualcomm Snapdragon X Plus (X1P-64-100) or above |
| Used in CPUs | - Apple M3 Pro | - Qualcomm Snapdragon X Plus (X1P-66-100) - Qualcomm Snapdragon X Elite (X1E-78-100) - Qualcomm Snapdragon X Elite (X1E-80-100) - Qualcomm Snapdragon X Plus (X1P-64-100) - Qualcomm Snapdragon X Elite (X1E-84-100) |
Laptop GPU ranking (61st and 112th place)
Graphics Processing Unit
| Base Clock | 500 MHz | 300 MHz |
| Boost Clock | 1380 MHz | 1200-1500 MHz (configurable) |
| Shading Units | 2304 | 1536 |
| Texture Mapping Units (TMUs) | 144 | 96 |
| Render Output Units (ROPs) | 72 | 48 |
| Compute Units (Pipelines) | 288 | 6 |
| Ray-tracing Cores | - | No |
| L1 Cache | - | 192KB per cluster |
| L2 Cache | - | 1MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 99 GPixel/s | 58-72 GPixel/s |
| Texture Fill Rate | 199 GTexel/s | 115-144 GTexel/s |
FLOPS (FP32)
Physical
| Interface | Custom | IGP |
| TGP | 30 W | 30 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 3 nm | 4 nm |
| Transistor Count | 25.2 billion | - |
| Max. Temperature | 100°C | - |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | 6400 MHz | - |
| Effective Memory Speed | 12800 Mbps | - |
| Bus | 192-bit | - |
| ECC | No | - |
Memory Bandwidth
API
| DirectX | - | 12.1 |
| Vulkan | - | 1.3 |
| OpenGL | - | 3.2 |
| OpenCL | - | 3.0 |
| CUDA | - | No |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | - | 1.4 |
Cast your vote
Total votes: 4