Moorechip Retroid Pocket 4 Pro
Geekbench AI Score
900
Single Precision Score
901
Half Precision Score
1713
Quantized Score
Geekbench AI 1.4.0 for Android AArch64
Result Information
| User | eunu |
| Upload Date | August 03 2025 12:58 AM |
| Views | 11 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | ARM MT8797Z/CNZA |
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Moorechip Retroid Pocket 4 Pro |
| Model ID | Moorechip Retroid Pocket 4 Pro |
| Motherboard | tb8797p1_64_k419 |
| CPU Information | |
|---|---|
| Name | ARM MT8797Z/CNZA |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 4 Cores @ 2.00 GHz |
| Cluster 2 | 4 Cores @ 2.60 GHz |
| Memory Information | |
|---|---|
| Size | 7.70 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
502
93.4 IPS |
|
|
Image Classification (HP)
|
100% |
508
94.5 IPS |
|
|
Image Classification (Q)
|
100% |
1558
289.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
635
10.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
636
10.3 IPS |
|
|
Image Segmentation (Q)
|
98% |
1831
29.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
2056
2.40 IPS |
|
|
Pose Estimation (HP)
|
100% |
1929
2.25 IPS |
|
|
Pose Estimation (Q)
|
84% |
3236
3.84 IPS |
|
|
Object Detection (SP)
|
100% |
338
26.8 IPS |
|
|
Object Detection (HP)
|
100% |
389
30.8 IPS |
|
|
Object Detection (Q)
|
83% |
1127
91.0 IPS |
|
|
Face Detection (SP)
|
100% |
1266
15.0 IPS |
|
|
Face Detection (HP)
|
100% |
1233
14.6 IPS |
|
|
Face Detection (Q)
|
95% |
3115
37.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
1554
12.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
1589
12.2 IPS |
|
|
Depth Estimation (Q)
|
64% |
2842
26.0 IPS |
|
|
Style Transfer (SP)
|
89% |
3396
4.41 IPS |
|
|
Style Transfer (HP)
|
89% |
3369
4.37 IPS |
|
|
Style Transfer (Q)
|
98% |
7269
9.37 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
856
31.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
852
31.5 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
986
36.5 IPS |
|
|
Text Classification (SP)
|
100% |
433
578.4 IPS |
|
|
Text Classification (HP)
|
100% |
419
559.0 IPS |
|
|
Text Classification (Q)
|
88% |
937
1.26 KIPS |
|
|
Machine Translation (SP)
|
100% |
636
11.0 IPS |
|
|
Machine Translation (HP)
|
100% |
624
10.7 IPS |
|
|
Machine Translation (Q)
|
50% |
352
12.5 IPS |
