realme RMX3921
Geekbench ML Score
615
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | October 03 2024 06:23 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 | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
287
53.7 IPS |
|
|
Image Classification (F16)
|
100% |
298
55.8 IPS |
|
|
Image Classification (I8)
|
97% |
758
141.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
358
5.98 IPS |
|
|
Image Segmentation (F16)
|
100% |
359
6.00 IPS |
|
|
Image Segmentation (I8)
|
98% |
560
9.36 IPS |
|
|
Pose Estimation (F32)
|
100% |
515
0.62 IPS |
|
|
Pose Estimation (F16)
|
100% |
517
0.63 IPS |
|
|
Pose Estimation (I8)
|
100% |
3036
3.68 IPS |
|
|
Object Detection (F32)
|
100% |
325
24.3 IPS |
|
|
Object Detection (F16)
|
100% |
327
24.4 IPS |
|
|
Object Detection (I8)
|
61% |
905
67.6 IPS |
|
|
Face Detection (F32)
|
100% |
555
6.60 IPS |
|
|
Face Detection (F16)
|
100% |
548
6.51 IPS |
|
|
Face Detection (I8)
|
86% |
1617
19.2 IPS |
|
|
Depth Estimation (F32)
|
100% |
522
4.04 IPS |
|
|
Depth Estimation (F16)
|
100% |
529
4.10 IPS |
|
|
Depth Estimation (I8)
|
95% |
1566
12.1 IPS |
|
|
Style Transfer (F32)
|
100% |
904
1.19 IPS |
|
|
Style Transfer (F16)
|
100% |
897
1.18 IPS |
|
|
Style Transfer (I8)
|
98% |
2686
3.53 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
420
15.0 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
425
15.2 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1415
50.5 IPS |
|
|
Text Classification (F32)
|
100% |
427
613.2 IPS |
|
|
Text Classification (F16)
|
100% |
445
640.2 IPS |
|
|
Text Classification (I8)
|
92% |
445
639.4 IPS |
|
|
Machine Translation (F32)
|
100% |
645
11.9 IPS |
|
|
Machine Translation (F16)
|
100% |
641
11.8 IPS |
|
|
Machine Translation (I8)
|
64% |
324
5.97 IPS |
