Anbernic RG405M vs Anbernic RG405M
| Anbernic RG405M | Anbernic RG405M | Difference | |
|---|---|---|---|
| Single Precision | 68 | 68 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Half Precision | 69 | 69 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Quantized | 102 | 102 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Geekbench AI 1.4.0 | Geekbench AI 1.4.0 | ||
System Information
| Anbernic RG405M | Anbernic RG405M | |
|---|---|---|
| AI Framework | TensorFlow Lite | TensorFlow Lite |
| AI Backend | NNAPI | NNAPI |
| AI Device | ARM Unisoc | ARM Unisoc |
| Operating System | Android 12 | Android 12 |
| Model | Anbernic RG405M | Anbernic RG405M |
| Processor |
ARM Unisoc @ 2.00 GHz
1 Processor, 8 Cores |
ARM Unisoc @ 2.00 GHz
1 Processor, 8 Cores |
| Processor ID | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
| Motherboard | ums512_1h10 | ums512_1h10 |
| Memory | 3.46 GB | 3.46 GB |
AI Performance
| Anbernic RG405M | Anbernic RG405M | Difference | |
|---|---|---|---|
| Image Classification (SP) | 41 | 41 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Classification (HP) | 41 | 41 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Classification (Q) | 266 | 266 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Segmentation (SP) | 58 | 58 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Segmentation (HP) | 57 | 57 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Segmentation (Q) | 186 | 186 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Pose Estimation (SP) | 79 | 79 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Pose Estimation (HP) | 79 | 79 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Pose Estimation (Q) | 0 | 0 | |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Object Detection (SP) | 42 | 42 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Object Detection (HP) | 42 | 42 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Object Detection (Q) | 236 | 236 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Face Detection (SP) | 87 | 87 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Face Detection (HP) | 88 | 88 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Face Detection (Q) | 496 | 496 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Depth Estimation (SP) | 86 | 86 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Depth Estimation (HP) | 90 | 90 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Depth Estimation (Q) | 232 | 232 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Style Transfer (SP) | 148 | 148 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Style Transfer (HP) | 148 | 148 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Style Transfer (Q) | 522 | 522 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Super-Resolution (SP) | 47 | 47 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Super-Resolution (HP) | 47 | 47 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Image Super-Resolution (Q) | 617 | 617 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Text Classification (SP) | 62 | 62 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Text Classification (HP) | 62 | 62 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Text Classification (Q) | 9 | 9 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Machine Translation (SP) | 87 | 87 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Machine Translation (HP) | 94 | 94 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
| Machine Translation (Q) | 34 | 34 | 100.0% |
| Anbernic RG405M | |||
| Anbernic RG405M | |||
