Google Pixel 4a
Geekbench ML Score
244
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 05 2023 12:57 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google Pixel 4a |
| Model ID | Google Pixel 4a |
| Motherboard | sunfish |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 6 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.21 GHz |
| Memory Information | |
|---|---|
| Size | 5.46 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
162
17.4 IPS |
|
|
Image Classification (F16)
|
100% |
163
17.4 IPS |
|
|
Image Classification (I8)
|
81% |
267
28.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
342
2.11 IPS |
|
|
Image Segmentation (F16)
|
100% |
339
2.09 IPS |
|
|
Image Segmentation (I8)
|
89% |
630
3.89 IPS |
|
|
Pose Estimation (F32)
|
100% |
145
0.59 IPS |
|
|
Pose Estimation (F16)
|
100% |
141
0.57 IPS |
|
|
Pose Estimation (I8)
|
80% |
154
0.62 IPS |
|
|
Object Detection (F32)
|
100% |
222
7.79 IPS |
|
|
Object Detection (F16)
|
100% |
219
7.70 IPS |
|
|
Object Detection (I8)
|
52% |
270
9.47 IPS |
|
|
Face Detection (F32)
|
100% |
325
3.73 IPS |
|
|
Face Detection (F16)
|
100% |
329
3.78 IPS |
|
|
Face Detection (I8)
|
75% |
482
5.54 IPS |
|
|
Text Classification (F32)
|
100% |
171
67.7 IPS |
|
|
Text Classification (F16)
|
100% |
257
101.5 IPS |
|
|
Machine Translation (F32)
|
100% |
224
34.5 IPS |
|
|
Machine Translation (F16)
|
100% |
218
33.6 IPS |
