[ APPLE ]
Graphics Cards
Apple M3 Pro GPU (18-core)
Overall Score
34/100
Key Technical Specifications
Graphics (GPU)
Apple M GPU
[ EXPERT VERDICT · SUMMARY ]
Apple M3 Pro GPU (18-core) is an engineering-tested graphics cards achieving an overall rating of 34/100. It is positioned for balanced everyday compute and power efficiency.
Benchmark Performance Scores
Normalized 0–100 Scale
Efficiency
Rating: Excellent
90/100
Gaming
Rating: Poor
19/100
Detailed Technical Specifications
3D Mark
| Specification | Value |
|---|---|
| Solar Bay | 22637 |
| Wild Life Extreme | 14021 |
API
| Specification | Value |
|---|---|
| DLSS | No |
| Ray Tracing | Yes |
GeekBench 6 ML
| Specification | Value |
|---|---|
| Backend | GPU |
| Depth Estimation (Q) | 23344 |
| Face Detection (HP) | 19900 |
| Framework | Core ML |
| Image Classification (SP) | 5578 |
| Image Segmentation (HP) | 9924 |
| Image Super Resolution (Q) | 13323 |
| Machine Translation (HP) | 4985 |
| Object Detection (SP) | 5496 |
| Pose Estimation (Q) | 35730 |
| Style Transfer (SP) | 78342 |
| Text Classification (SP) | 2904 |
GeekBench 6 OpenCL
| Specification | Value |
|---|---|
| API | OpenCL |
| Background Blur | 82.1 img/sec |
| Edge Detection | 2.59 Gpixels/sec |
| Face Detection | 53.6 img/sec |
| Feature Matching | 0.48 Gpixels/sec |
| Gaussian Blur | 1.84 Gpixels/sec |
| Horizon Detection | 1.82 Gpixels/sec |
| Particle Physics | 4893.9 FPS |
| Stereo Matching | 148.6 Gpixels/sec |
General
| Specification | Value |
|---|---|
| Architecture | Apple M GPU |
| Build | Integrated |
| Case | Laptop |
| GPU Codename | Custom |
| Nvidia Equivalent | -GeForce RTX 4060 Laptop |
| Purpose | Professional |
| Recommended CPU | -Apple M3 Proor above |
| Released | October 31, 2023 |
| Segment | Mid-range |
| Successor | -Apple M5 Pro GPU (20-core) |
| Used in CPUs | -Apple M3 Pro |
| Vendor | Apple |
Graphics Processing Unit
| Specification | Value |
|---|---|
| Base Clock | 500 MHz |
| Boost Clock | 1380 MHz |
| Compute Units (Pipelines) | 288 |
| Instructions Per Cycle | 2 IPC |
| Render Output Units (ROPs) | 72 |
| Shading Units | 2304 |
| Texture Mapping Units (TMUs) | 144 |
Memory
| Specification | Value |
|---|---|
| Bus | 192-bit |
| ECC | No |
| Effective Memory Speed | 12800 Mbps |
| Memory Clock | 6400 MHz |
| Memory Type | System Shared |
Physical
| Specification | Value |
|---|---|
| Fabrication Process | 3 nm |
| Interface | Custom |
| Manufacturing | TSMC |
| Max. Temperature | 100°C |
| TGP | 30 W |
| Transistor Count | 25.2 billion |
Raw Performance
| Specification | Value |
|---|---|
| Pixel Fill Rate | 99 GPixel/s |
| Texture Fill Rate | 199 GTexel/s |
Strengths & Limitations
Key Advantages
- Comprehensive positive benchmark metrics recorded.
Key Considerations
- No major hardware limitations flagged during benchmark run.
Direct Competitors & Alternatives
NVIDIA
Nvidia RTX Pro 6000 Blackwell
98/100
Compare →
GEFORCE
GeForce RTX 5090
96/100
Compare →
GEFORCE
GeForce RTX 4090
89/100
Compare →
AMD
AMD Radeon RX 7900 XTX
85/100
Compare →
Methodology, Provenance & Verification
Score version 2026.1 · Data verified 2026-08-26 · Source: official manufacturer datasheets and standardized reproducible benchmark suites (Geekbench 6, Cinebench R24, 3DMark).