realme RMX3921
Geekbench ML Score
285
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | October 03 2024 07:14 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | realme RMX3921 |
| Model ID | realme RMX3921 |
| Motherboard | parrot |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
| Base Frequency | 1.96 GHz |
| Cluster 1 | 4 Cores @ 1.96 GHz |
| Cluster 2 | 4 Cores @ 2.40 GHz |
| Memory Information | |
|---|---|
| Size | 7.24 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
123
23.0 IPS |
|
|
Image Classification (F16)
|
100% |
123
23.1 IPS |
|
|
Image Classification (I8)
|
97% |
334
62.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
163
2.73 IPS |
|
|
Image Segmentation (F16)
|
100% |
163
2.72 IPS |
|
|
Image Segmentation (I8)
|
98% |
365
6.09 IPS |
|
|
Pose Estimation (F32)
|
100% |
221
0.27 IPS |
|
|
Pose Estimation (F16)
|
100% |
220
0.27 IPS |
|
|
Pose Estimation (I8)
|
100% |
845
1.02 IPS |
|
|
Object Detection (F32)
|
100% |
130
9.71 IPS |
|
|
Object Detection (F16)
|
100% |
130
9.71 IPS |
|
|
Object Detection (I8)
|
61% |
378
28.2 IPS |
|
|
Face Detection (F32)
|
100% |
315
3.75 IPS |
|
|
Face Detection (F16)
|
100% |
319
3.79 IPS |
|
|
Face Detection (I8)
|
86% |
736
8.75 IPS |
|
|
Depth Estimation (F32)
|
100% |
274
2.13 IPS |
|
|
Depth Estimation (F16)
|
100% |
274
2.12 IPS |
|
|
Depth Estimation (I8)
|
95% |
776
6.02 IPS |
|
|
Style Transfer (F32)
|
100% |
466
0.61 IPS |
|
|
Style Transfer (F16)
|
100% |
467
0.61 IPS |
|
|
Style Transfer (I8)
|
98% |
1308
1.72 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
142
5.07 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
141
5.05 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
501
17.9 IPS |
|
|
Text Classification (F32)
|
100% |
164
236.4 IPS |
|
|
Text Classification (F16)
|
100% |
167
239.4 IPS |
|
|
Text Classification (I8)
|
92% |
322
462.3 IPS |
|
|
Machine Translation (F32)
|
100% |
300
5.53 IPS |
|
|
Machine Translation (F16)
|
100% |
300
5.52 IPS |
|
|
Machine Translation (I8)
|
64% |
387
7.13 IPS |
