Google Pixel 6a
Geekbench ML Score
1423
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 11 2023 07:56 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google Pixel 6a |
| Model ID | Google Pixel 6a |
| Motherboard | bluejay |
| Governor | sched_pixel |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.25 GHz |
| Cluster 3 | 2 Cores @ 2.80 GHz |
| Memory Information | |
|---|---|
| Size | 5.44 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
697
74.7 IPS |
|
|
Image Classification (F16)
|
100% |
1265
135.5 IPS |
|
|
Image Classification (I8)
|
80% |
982
105.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
2955
18.3 IPS |
|
|
Image Segmentation (F16)
|
100% |
4920
30.4 IPS |
|
|
Image Segmentation (I8)
|
89% |
5012
31.0 IPS |
|
|
Pose Estimation (F32)
|
100% |
921
3.73 IPS |
|
|
Pose Estimation (F16)
|
100% |
2799
11.3 IPS |
|
|
Pose Estimation (I8)
|
80% |
2830
11.4 IPS |
|
|
Object Detection (F32)
|
100% |
700
24.6 IPS |
|
|
Object Detection (F16)
|
100% |
846
29.7 IPS |
|
|
Object Detection (I8)
|
54% |
849
29.8 IPS |
|
|
Face Detection (F32)
|
100% |
1978
22.7 IPS |
|
|
Face Detection (F16)
|
97% |
3167
36.4 IPS |
|
|
Face Detection (I8)
|
75% |
2739
31.5 IPS |
|
|
Text Classification (F32)
|
100% |
507
200.5 IPS |
|
|
Text Classification (F16)
|
98% |
859
339.9 IPS |
|
|
Machine Translation (F32)
|
100% |
686
105.8 IPS |
|
|
Machine Translation (F16)
|
100% |
692
106.7 IPS |
