realme RMX3472
Geekbench ML Score
497
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | December 02 2023 03:55 AM |
| Views | 2 |
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 |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
355
38.0 IPS |
|
|
Image Classification (F16)
|
100% |
511
54.7 IPS |
|
|
Image Classification (I8)
|
80% |
1528
163.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
719
4.44 IPS |
|
|
Image Segmentation (F16)
|
100% |
1078
6.66 IPS |
|
|
Image Segmentation (I8)
|
89% |
3100
19.2 IPS |
|
|
Pose Estimation (F32)
|
100% |
148
0.60 IPS |
|
|
Pose Estimation (F16)
|
100% |
302
1.22 IPS |
|
|
Pose Estimation (I8)
|
80% |
1477
5.98 IPS |
|
|
Object Detection (F32)
|
100% |
398
14.0 IPS |
|
|
Object Detection (F16)
|
100% |
504
17.7 IPS |
|
|
Object Detection (I8)
|
52% |
822
28.9 IPS |
|
|
Face Detection (F32)
|
100% |
505
5.80 IPS |
|
|
Face Detection (F16)
|
97% |
863
9.92 IPS |
|
|
Face Detection (I8)
|
75% |
2384
27.4 IPS |
|
|
Text Classification (F32)
|
100% |
18
7.04 IPS |
|
|
Text Classification (F16)
|
100% |
109
43.3 IPS |
|
|
Machine Translation (F32)
|
100% |
341
52.6 IPS |
|
|
Machine Translation (F16)
|
100% |
339
52.3 IPS |
