realme RMX3921
Geekbench ML Score
307
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | October 03 2024 06:35 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 | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
164
30.8 IPS |
|
|
Image Classification (F16)
|
100% |
247
46.2 IPS |
|
|
Image Classification (I8)
|
97% |
238
44.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
263
4.39 IPS |
|
|
Image Segmentation (F16)
|
100% |
316
5.28 IPS |
|
|
Image Segmentation (I8)
|
98% |
316
5.27 IPS |
|
|
Pose Estimation (F32)
|
100% |
200
0.24 IPS |
|
|
Pose Estimation (F16)
|
100% |
297
0.36 IPS |
|
|
Pose Estimation (I8)
|
100% |
299
0.36 IPS |
|
|
Object Detection (F32)
|
100% |
140
10.4 IPS |
|
|
Object Detection (F16)
|
100% |
177
13.2 IPS |
|
|
Object Detection (I8)
|
62% |
175
13.1 IPS |
|
|
Face Detection (F32)
|
100% |
472
5.62 IPS |
|
|
Face Detection (F16)
|
97% |
628
7.47 IPS |
|
|
Face Detection (I8)
|
87% |
587
6.98 IPS |
|
|
Depth Estimation (F32)
|
100% |
328
2.55 IPS |
|
|
Depth Estimation (F16)
|
100% |
519
4.02 IPS |
|
|
Depth Estimation (I8)
|
95% |
502
3.89 IPS |
|
|
Style Transfer (F32)
|
100% |
733
0.96 IPS |
|
|
Style Transfer (F16)
|
100% |
1345
1.77 IPS |
|
|
Style Transfer (I8)
|
98% |
1390
1.83 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
137
4.89 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
161
5.77 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
160
5.73 IPS |
|
|
Text Classification (F32)
|
100% |
167
239.3 IPS |
|
|
Text Classification (F16)
|
100% |
167
239.7 IPS |
|
|
Text Classification (I8)
|
92% |
321
461.9 IPS |
|
|
Machine Translation (F32)
|
100% |
300
5.53 IPS |
|
|
Machine Translation (F16)
|
100% |
301
5.53 IPS |
|
|
Machine Translation (I8)
|
64% |
388
7.14 IPS |
