Xiaomi 22031116AI
Geekbench ML Score
189
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | May 08 2024 06:06 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Xiaomi 22031116AI |
| Model ID | Xiaomi 22031116AI |
| Motherboard | evergo |
| CPU Information | |
|---|---|
| Name | ARM MT6833P |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 6 Cores @ 2.00 GHz |
| Cluster 2 | 2 Cores @ 2.40 GHz |
| Memory Information | |
|---|---|
| Size | 7.45 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
106
19.8 IPS |
|
|
Image Classification (F16)
|
100% |
196
36.7 IPS |
|
|
Image Classification (I8)
|
97% |
173
32.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
137
2.29 IPS |
|
|
Image Segmentation (F16)
|
100% |
242
4.03 IPS |
|
|
Image Segmentation (I8)
|
98% |
233
3.90 IPS |
|
|
Pose Estimation (F32)
|
100% |
96
0.12 IPS |
|
|
Pose Estimation (F16)
|
100% |
110
0.13 IPS |
|
|
Pose Estimation (I8)
|
100% |
110
0.13 IPS |
|
|
Object Detection (F32)
|
100% |
92
6.87 IPS |
|
|
Object Detection (F16)
|
100% |
135
10.1 IPS |
|
|
Object Detection (I8)
|
62% |
149
11.1 IPS |
|
|
Face Detection (F32)
|
100% |
309
3.67 IPS |
|
|
Face Detection (F16)
|
98% |
491
5.84 IPS |
|
|
Face Detection (I8)
|
86% |
382
4.55 IPS |
|
|
Depth Estimation (F32)
|
100% |
185
1.44 IPS |
|
|
Depth Estimation (F16)
|
100% |
236
1.83 IPS |
|
|
Depth Estimation (I8)
|
95% |
234
1.82 IPS |
|
|
Style Transfer (F32)
|
100% |
364
0.48 IPS |
|
|
Style Transfer (F16)
|
100% |
503
0.66 IPS |
|
|
Style Transfer (I8)
|
98% |
504
0.66 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
95
3.38 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
145
5.17 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
154
5.51 IPS |
|
|
Text Classification (F32)
|
100% |
109
156.6 IPS |
|
|
Text Classification (F16)
|
100% |
107
154.3 IPS |
|
|
Text Classification (I8)
|
92% |
172
247.9 IPS |
|
|
Machine Translation (F32)
|
100% |
273
5.02 IPS |
|
|
Machine Translation (F16)
|
100% |
201
3.71 IPS |
|
|
Machine Translation (I8)
|
64% |
263
4.84 IPS |
