AMD Radeon RX Vega 8 vs Apple M2 Pro GPU (19-core)
We compared two integrated laptop graphics cards: the Radeon RX Vega 8 with 8 pipelines and 512 shaders against the 5 years newer Apple M2 Pro GPU (19-core) that utilizes 304 pipelines and 2432 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
DeviceFacts Final Score
Overall video card score
Key differences
Reasons to consider the Apple M2 Pro GPU (19-core)
- Performs significantly better (up to 4.1x) in 3DMark Steel Nomad Lite
- 3.1x higher maximum theoretical performance (6.8 vs 2.2 TFLOPS)
- Manufactured using a more efficient 5 nm process technology
- Achieves 4.7x more points in the GeekBench 6 Compute test (49K vs 10K)
- Has 4.8x more shading units (2432 vs 512)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 25 11 10 - |
- |
| The Witcher 3 | 9 10 - - |
- |
| Counter-Strike 2 | 27 16 12 - |
- |
| Far Cry 6 | 20 17 10 - |
- |
| Hogwarts Legacy | 11 - - - |
- |
| CoD: Modern Warfare III | 22 17 14 - |
- |
| Ghost of Tsushima | 12 9 - - |
- |
| Cyberpunk 2077 | - - - - |
- |
| Shadow of the Tomb Raider | 14 13 10 - |
- |
| 1080p High | 16 | - |
| 1080p Ultra | 12 | - |
| 1440p Ultra | 9 | - |
| 4K Ultra | - | - |
| Margin of Error | Low | High |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 1410 | - |
| Solar Bay | - | 16218 |
| Fire Strike | 4497 | - |
| Wild Life Extreme | 2532 | 12726 |
| Night Raid | 18010 | - |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 21.2 img/sec | 89.7 img/sec |
| Face Detection | 10.9 img/sec | 58 img/sec |
| Horizon Detection | 0.34 Gpixels/sec | 1.94 Gpixels/sec |
| Edge Detection | 0.65 Gpixels/sec | 3.26 Gpixels/sec |
| Gaussian Blur | 0.51 Gpixels/sec | 2.19 Gpixels/sec |
| Feature Matching | 0.13 Gpixels/sec | 0.55 Gpixels/sec |
| Stereo Matching | 34.9 Gpixels/sec | 163 Gpixels/sec |
| Particle Physics | 1322.9 FPS | 6139.2 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 398 | - |
| DirectX 11 | 10 FPS | - |
| DirectX 12 | 8 FPS | - |
| GPU Compute | 861 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) | 924 | 5279 |
| Image Segmentation (HP) | 1148 | 8089 |
| Image Super Resolution (Q) | 2211 | 15007 |
| Face Detection (HP) | 2819 | 19212 |
| Pose Estimation (Q) | 7106 | 44046 |
| Text Classification (SP) | 832 | 2280 |
| Machine Translation (HP) | 1021 | 1972 |
| Object Detection (SP) | 1040 | 4941 |
| Depth Estimation (Q) | 3885 | 22209 |
| Style Transfer (SP) | 14495 | 79898 |
| Framework | ONNX | Core ML |
| Backend | DirectML | GPU |
Results were compared using different ML frameworks
Specifications
Technical specifications of Radeon RX Vega 8 and Apple M2 Pro GPU (19-core)General
| Vendor | Amd | Apple |
| Build | Integrated | Integrated |
| Released | February 13, 2018 | January 17, 2023 |
| Case | Laptop | Laptop |
| Purpose | Generic | Professional |
| Segment | Entry-level | High-end |
| Architecture | GCN 5.0 | Apple M GPU |
| GPU Codename | Raven | - |
| Rival Equivalent | - | - GeForce RTX 3050 Laptop |
| Successor | - | - Apple M5 Pro GPU (20-core) |
| Recommended CPU | - AMD Ryzen 7 4800U or above | - Apple M2 Pro or above |
| Used in CPUs | - AMD Ryzen 7 7730U - AMD Ryzen 7 5825U - AMD Ryzen 7 5700G - AMD Ryzen 7 Pro 5850U - AMD Ryzen 7 5800HS - AMD Ryzen 9 5980HX - AMD Ryzen 7 5700U - AMD Ryzen 9 5900HS - and 8 more |
- Apple M2 Pro |
Laptop GPU ranking (127th and 70th place)
Graphics Processing Unit
| Base Clock | 300 MHz | 450 MHz |
| Boost Clock | 1100-2100 MHz (configurable) | 1398 MHz |
| Shading Units | 512 | 2432 |
| Texture Mapping Units (TMUs) | 32 | 152 |
| Render Output Units (ROPs) | 8 | 76 |
| Compute Units (Pipelines) | 8 | 304 |
| Tensor Cores | No | - |
| Ray-tracing Cores | No | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 9-17 GPixel/s | 106 GPixel/s |
| Texture Fill Rate | 35-67 GTexel/s | 212 GTexel/s |
FLOPS (FP32)
Physical
| Interface | IGP | Custom |
| TGP | 25 W | 35 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 7 nm | 5 nm |
| Die Size | 210 mm² | - |
| Transistor Count | 4.94 billion | 26 billion |
| Transistor Density | 23.52 MTr/mm² | - |
| Max. Temperature | - | 94°C |
Memory
| Memory Type | System Shared | System Shared |
| Memory Size | System RAM Dependent | - |
| Memory Clock | System RAM Dependent | 6400 MHz |
| Effective Memory Speed | System RAM Dependent | 12800 Mbps |
| Bus | - | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | - |
| Vulkan | 1.3 | - |
| OpenGL | 4.6 | - |
| OpenCL | 2.0 | - |
| Ray Tracing | No | No |
| DLSS | No | No |
Cast your vote
Total votes: < 1