Xiaomi 21061119BI
Geekbench ML Score
94
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | May 07 2024 10:49 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Xiaomi 21061119BI |
| Model ID | Xiaomi 21061119BI |
| Motherboard | selene |
| CPU Information | |
|---|---|
| Name | ARM MT6769H |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 6 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.00 GHz |
| Memory Information | |
|---|---|
| Size | 5.58 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
49
9.23 IPS |
|
|
Image Classification (F16)
|
100% |
43
8.10 IPS |
|
|
Image Classification (I8)
|
97% |
83
15.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
58
0.96 IPS |
|
|
Image Segmentation (F16)
|
100% |
58
0.97 IPS |
|
|
Image Segmentation (I8)
|
98% |
93
1.55 IPS |
|
|
Pose Estimation (F32)
|
100% |
83
0.10 IPS |
|
|
Pose Estimation (F16)
|
100% |
83
0.10 IPS |
|
|
Pose Estimation (I8)
|
100% |
173
0.21 IPS |
|
|
Object Detection (F32)
|
100% |
46
3.46 IPS |
|
|
Object Detection (F16)
|
100% |
46
3.46 IPS |
|
|
Object Detection (I8)
|
61% |
89
6.63 IPS |
|
|
Face Detection (F32)
|
100% |
116
1.38 IPS |
|
|
Face Detection (F16)
|
100% |
116
1.38 IPS |
|
|
Face Detection (I8)
|
86% |
215
2.55 IPS |
|
|
Depth Estimation (F32)
|
100% |
108
0.84 IPS |
|
|
Depth Estimation (F16)
|
100% |
105
0.81 IPS |
|
|
Depth Estimation (I8)
|
95% |
200
1.55 IPS |
|
|
Style Transfer (F32)
|
100% |
198
0.26 IPS |
|
|
Style Transfer (F16)
|
100% |
197
0.26 IPS |
|
|
Style Transfer (I8)
|
98% |
373
0.49 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
55
1.95 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
60
2.15 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
111
3.96 IPS |
|
|
Text Classification (F32)
|
100% |
59
84.4 IPS |
|
|
Text Classification (F16)
|
100% |
59
84.9 IPS |
|
|
Text Classification (I8)
|
92% |
83
119.2 IPS |
|
|
Machine Translation (F32)
|
100% |
116
2.14 IPS |
|
|
Machine Translation (F16)
|
100% |
115
2.11 IPS |
|
|
Machine Translation (I8)
|
64% |
118
2.16 IPS |
