Xiaomi 12T Pro
Geekbench ML Score
281
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | July 26 2024 01:44 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Xiaomi 12T Pro |
| Model ID | Xiaomi 22081212UG |
| Motherboard | diting |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 4 Cores @ 2.02 GHz |
| Cluster 2 | 3 Cores @ 2.75 GHz |
| Cluster 3 | 1 Core @ 3.19 GHz |
| Memory Information | |
|---|---|
| Size | 10.93 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
121
22.6 IPS |
|
|
Image Classification (F16)
|
100% |
121
22.6 IPS |
|
|
Image Classification (I8)
|
97% |
319
59.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
155
2.58 IPS |
|
|
Image Segmentation (F16)
|
100% |
155
2.58 IPS |
|
|
Image Segmentation (I8)
|
98% |
337
5.63 IPS |
|
|
Pose Estimation (F32)
|
100% |
213
0.26 IPS |
|
|
Pose Estimation (F16)
|
100% |
213
0.26 IPS |
|
|
Pose Estimation (I8)
|
100% |
814
0.99 IPS |
|
|
Object Detection (F32)
|
100% |
127
9.46 IPS |
|
|
Object Detection (F16)
|
100% |
127
9.45 IPS |
|
|
Object Detection (I8)
|
61% |
359
26.8 IPS |
|
|
Face Detection (F32)
|
100% |
323
3.84 IPS |
|
|
Face Detection (F16)
|
100% |
324
3.85 IPS |
|
|
Face Detection (I8)
|
86% |
714
8.49 IPS |
|
|
Depth Estimation (F32)
|
100% |
277
2.15 IPS |
|
|
Depth Estimation (F16)
|
100% |
277
2.15 IPS |
|
|
Depth Estimation (I8)
|
95% |
795
6.16 IPS |
|
|
Style Transfer (F32)
|
100% |
482
0.63 IPS |
|
|
Style Transfer (F16)
|
100% |
484
0.64 IPS |
|
|
Style Transfer (I8)
|
98% |
1310
1.72 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
143
5.12 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
144
5.14 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
504
18.0 IPS |
|
|
Text Classification (F32)
|
100% |
166
238.3 IPS |
|
|
Text Classification (F16)
|
100% |
166
237.9 IPS |
|
|
Text Classification (I8)
|
92% |
297
426.5 IPS |
|
|
Machine Translation (F32)
|
100% |
301
5.54 IPS |
|
|
Machine Translation (F16)
|
100% |
300
5.51 IPS |
|
|
Machine Translation (I8)
|
64% |
365
6.73 IPS |
