AMD Radeon 840M vs Apple A18 Pro GPU
VS
AMD Radeon 840M
Krackan Point
Apple A18 Pro GPU
Custom
We compared two integrated laptop GPUs: the Radeon 840M with 4 pipelines and 256 shaders against the 4 months older Apple A18 Pro GPU that utilizes 128 pipelines and 768 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 A18 Pro GPU
- Performs better (up to 36%) in 3DMark Steel Nomad Lite
- 53% higher maximum theoretical performance (2.3 vs 1.5 TFLOPS)
- Manufactured using a more efficient 3 nm process technology
- Achieves 2.2x more points in the GeekBench 6 Compute test (31K vs 14K)
- Has 3x more shading units (768 vs 256)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 25 14 12 - |
- |
| The Witcher 3 | 11 12 - - |
- |
| Counter-Strike 2 | 27 20 14 - |
- |
| Far Cry 6 | 21 17 12 - |
- |
| Hogwarts Legacy | 11 - - - |
- |
| CoD: Modern Warfare III | 22 19 14 9 |
- |
| Ghost of Tsushima | 13 10 - - |
- |
| Cyberpunk 2077 | 10 10 - - |
- |
| Shadow of the Tomb Raider | 16 18 11 - |
- |
| 1080p High | 17 | - |
| 1080p Ultra | 14 | - |
| 1440p Ultra | 10 | - |
| 4K Ultra | - | - |
| Margin of Error | High | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 1699 | - |
| Solar Bay | 6960 | 7374 |
| Port Royal | 553 | - |
| Fire Strike | 5303 | - |
| Wild Life Extreme | 2671 | 3947 |
| Night Raid | 22563 | - |
GeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | 31.8 img/sec | 57.1 img/sec |
| Face Detection | 16.8 img/sec | 91.4 img/sec |
| Horizon Detection | 0.46 Gpixels/sec | 0.92 Gpixels/sec |
| Edge Detection | 0.58 Gpixels/sec | 1.21 Gpixels/sec |
| Gaussian Blur | 0.42 Gpixels/sec | 1.5 Gpixels/sec |
| Feature Matching | 0.18 Gpixels/sec | 0.45 Gpixels/sec |
| Stereo Matching | 52.5 Gpixels/sec | 84.2 Gpixels/sec |
| Particle Physics | 2048.6 FPS | 3061 FPS |
| API | OpenCL | Metal |
Passmark Graphics
G3D Mark Score
| G2D Mark | 866 | - |
| DirectX 11 | 32 FPS | - |
| DirectX 12 | 17 FPS | - |
| GPU Compute | 1689 Ops/s | - |
Recent User Tests
Radeon 840M
No benchmark results yet
Apple A18 Pro GPU
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-04-24 -> Rennsport | Geekbench 6 OpenCL | 19670 |
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) | 1988 | 3264 |
| Image Segmentation (HP) | 2184 | 4550 |
| Image Super Resolution (Q) | 4788 | 6705 |
| Face Detection (HP) | 6857 | 11770 |
| Pose Estimation (Q) | 17396 | 15548 |
| Text Classification (SP) | 1628 | 3678 |
| Machine Translation (HP) | 2053 | 5678 |
| Object Detection (SP) | 1825 | 3360 |
| Depth Estimation (Q) | 8471 | 13468 |
| Style Transfer (SP) | 31032 | 31541 |
| Framework | ONNX | Core ML |
| Backend | DirectML | GPU |
Results were compared using different ML frameworks
Specifications
Technical specifications of Radeon 840M and Apple A18 Pro GPUGeneral
| Vendor | Amd | Apple |
| Build | Integrated | Integrated |
| Released | January 7, 2025 | September 9, 2024 |
| Case | Laptop | Laptop |
| Purpose | Generic | Generic |
| Segment | Entry-level | Mid-range |
| Architecture | RDNA 3.5 | Apple M GPU |
| GPU Codename | Krackan Point | Custom |
| Rival Equivalent | - Intel Arc 130T | - |
| Recommended CPU | - AMD Ryzen AI 5 340 or above | - Apple A18 Pro (MacBook) or above |
| Used in CPUs | - AMD Ryzen AI 7 345 - AMD Ryzen AI 5 430 - AMD Ryzen AI 7 445 - AMD Ryzen AI 5 435 - AMD Ryzen AI 5 440 - AMD Ryzen AI 5 340 |
- Apple A18 Pro (MacBook) |
Laptop GPU ranking (106th and 81st place)
Graphics Processing Unit
| Base Clock | 400 MHz | - |
| Boost Clock | 2900 MHz | 1490 MHz |
| Shading Units | 256 | 768 |
| Texture Mapping Units (TMUs) | 16 | 40 |
| Render Output Units (ROPs) | 8 | - |
| Compute Units (Pipelines) | 4 | 128 |
| Tensor Cores | No | - |
| Ray-tracing Cores | 4 | - |
| L1 Cache | 128KB per cluster | - |
| L2 Cache | 1MB shared | - |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 23 GPixel/s | - |
| Texture Fill Rate | 46 GTexel/s | 60 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x8 | Custom |
| TGP | 15 W | - |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 3 nm |
| Die Size | 195 mm² | - |
| Max. Temperature | 100°C | - |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | - | 7500 MHz |
| Bus | - | 128-bit |
| ECC | No | No |
API
| DirectX | 12 | - |
| Vulkan | 1.4 | - |
| OpenGL | 4.6 | - |
| OpenCL | 2.1 | - |
| CUDA | No | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1 | - |
Cast your vote
Total votes: < 1