Google Pixel 6a
Geekbench ML Score
1344
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 07 2022 02:53 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% |
663
71.1 IPS |
|
|
Image Classification (F16)
|
100% |
920
98.5 IPS |
|
|
Image Classification (I8)
|
80% |
957
102.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
2923
18.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
5073
31.3 IPS |
|
|
Image Segmentation (I8)
|
89% |
5098
31.5 IPS |
|
|
Pose Estimation (F32)
|
100% |
875
3.54 IPS |
|
|
Pose Estimation (F16)
|
100% |
2842
11.5 IPS |
|
|
Pose Estimation (I8)
|
80% |
2820
11.4 IPS |
|
|
Object Detection (F32)
|
100% |
577
20.3 IPS |
|
|
Object Detection (F16)
|
100% |
843
29.6 IPS |
|
|
Object Detection (I8)
|
54% |
872
30.6 IPS |
|
|
Face Detection (F32)
|
100% |
2033
23.4 IPS |
|
|
Face Detection (F16)
|
97% |
3005
34.5 IPS |
|
|
Face Detection (I8)
|
75% |
2428
27.9 IPS |
|
|
Text Classification (F32)
|
100% |
442
174.7 IPS |
|
|
Text Classification (F16)
|
98% |
689
272.7 IPS |
|
|
Machine Translation (F32)
|
100% |
687
105.9 IPS |
|
|
Machine Translation (F16)
|
100% |
682
105.1 IPS |
