realme RMX3472
Geekbench ML Score
451
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 16 2023 10:10 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | realme RMX3472 |
| Model ID | realme RMX3472 |
| Motherboard | holi |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 6 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.21 GHz |
| Memory Information | |
|---|---|
| Size | 7.24 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
343
36.7 IPS |
|
|
Image Classification (F16)
|
100% |
483
51.8 IPS |
|
|
Image Classification (I8)
|
80% |
1182
126.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
717
4.43 IPS |
|
|
Image Segmentation (F16)
|
100% |
1049
6.48 IPS |
|
|
Image Segmentation (I8)
|
89% |
2928
18.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
147
0.59 IPS |
|
|
Pose Estimation (F16)
|
100% |
302
1.22 IPS |
|
|
Pose Estimation (I8)
|
80% |
1448
5.86 IPS |
|
|
Object Detection (F32)
|
100% |
304
10.7 IPS |
|
|
Object Detection (F16)
|
100% |
361
12.7 IPS |
|
|
Object Detection (I8)
|
52% |
565
19.8 IPS |
|
|
Face Detection (F32)
|
100% |
495
5.68 IPS |
|
|
Face Detection (F16)
|
97% |
846
9.72 IPS |
|
|
Face Detection (I8)
|
75% |
2206
25.3 IPS |
|
|
Text Classification (F32)
|
100% |
15
5.84 IPS |
|
|
Text Classification (F16)
|
100% |
97
38.2 IPS |
|
|
Machine Translation (F32)
|
100% |
342
52.7 IPS |
|
|
Machine Translation (F16)
|
100% |
344
53.0 IPS |
