Quick/Comparisons
6 | Gaming | 13 |
9 | Workstation | 20 |
9 | AI/ML |
Compare with something else?
Compare Radeon 840M with another →12 |
86 | Energy Efficiency | 64 |
20 | Quick Comparison Final Score | 23 |
| Krackan Point | Graphics Processor | Navi 14 |
| 256 | Cores | 1408 |
| 16 / 8 | TMUs / ROPs | 88 / 32 |
| 122.02 | Blender GPU | 368.1 |
| 13 | Forza Horizon 5 | 39 |
| 12 | The Witcher 3 | 37 |
| 18 | Counter-Strike 2 | 48 |
| 16 | Far Cry 6 | 46 |
| - | Hogwarts Legacy | 25 |
| 19 | Call of Duty | 40 |
| 9 | Ghost of Tsushima | 20 |
| 9 | Cyberpunk 2077 | 27 |
| 17 | Tomb Raider | 46 |
| 13 | Average FPS | 36 |
| 18 | 1080p High | 48 |
| 13 | 1080p Ultra | 36 |
| 10 | 1440p Ultra | 24 |
| - | 4K Ultra | 13 |
| High | Margin of Error | Low |
| 14025 | GB6 Compute Score | 46415 |
| 31.8 img/sec | Background Blur | 89.3 img/sec |
| 16.8 img/sec | Face Detection | 50.3 img/sec |
| 0.46 Gpixels/sec | Horizon Detection | 1.91 Gpixels/sec |
| 0.58 Gpixels/sec | Edge Detection | 2.74 Gpixels/sec |
| 0.42 Gpixels/sec | Gaussian Blur | 2.25 Gpixels/sec |
| 0.18 Gpixels/sec | Feature Matching | 0.49 Gpixels/sec |
| 52.5 Gpixels/sec | Stereo Matching | 159.9 Gpixels/sec |
| 2048.6 FPS | Particle Physics | 5898.4 FPS |
| OpenCL | API | OpenCL |
| — | G3D Mark Score | 5998 |
| — | G2D Mark | 413 |
| — | DirectX 11 | 36 FPS |
| — | DirectX 12 | 29 FPS |
| — | GPU Compute | 2338 Ops/s |
| 4884 | GB6 ML Single Precision | 6824 |
| 6067 | GB6 ML Half Precision | 7661 |
| 3946 | GB6 ML Quantized | 5150 |
| 1988 | Image Classification (SP) | 2845 |
| 2184 | Image Segmentation (HP) | 3023 |
| 4788 | Image Super Resolution (Q) | 8505 |
| 6857 | Face Detection (HP) | 8964 |
| 17396 | Pose Estimation (Q) | 29278 |
| 1628 | Text Classification (SP) | 1142 |
| 2053 | Machine Translation (HP) | 1920 |
| 1825 | Object Detection (SP) | 3032 |
| 8471 | Depth Estimation (Q) | 14009 |
| 31032 | Style Transfer (SP) | 58664 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 23 GPixel/s | Pixel Fill Rate | 53 GPixel/s |
| 46 GTexel/s | Texture Fill Rate | 145 GTexel/s |
| 1.5 TFLOPS | FLOPS (FP32) | 4.6 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 4 GB |
| — | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 14000 Mbps |
| — | Bus | 128-bit |
| — | ECC | — |
| — | Memory Bandwidth | 224 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 15-54 W (configurable) | TGP | 85 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 7 nm |
| — | Die Size | 158 mm² |
| — | Transistor Count | 6.4 billion |
| — | Transistor Density | 40.51 MTr/mm² |
| 12 | DirectX | 12 |
| 1.4 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.1 |
| No | CUDA | — |
| Yes | Ray Tracing | No |
| No | DLSS | No |
| 2.1 | DisplayPort | 1.4 |
| Amd | Vendor | Amd |
| Integrated | Build | Discrete |
| January 7, 2025 | Released | October 7, 2019 |
| Laptop | Case | Laptop |
| Generic | Purpose | Gaming |
| Entry-level | Segment | High-end |
| RDNA 3.5 | Architecture | RDNA 1.0 |
| Krackan Point | GPU Codename | Navi 14 |
| -AMD Ryzen AI 5 340or above | Recommended CPU | -AMD Ryzen 5 5600Hor above |
| 1293 | Steel Nomad Lite Score | 3774 |
| 1700 | Time Spy | 4292 |
| 7155 | Solar Bay | — |
| 577 | Port Royal | — |
| 5317 | Fire Strike | 12807 |
| — | Wild Life Extreme | 6440 |
| 22727 | Night Raid | 42033 |
| 400 MHz | Base Clock | 1375 MHz |
| 2900 MHz | Boost Clock | 1645 MHz |
| 256 | Shading Units | 1408 |
| 16 | Texture Mapping Units (TMUs) | 88 |
| 8 | Render Output Units (ROPs) | 32 |
| 4 | Compute Units (Pipelines) | 22 |
| No | Tensor Cores | No |
| 4 | Ray-tracing Cores | No |
| 512KB per cluster | L1 Cache | — |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |