Google Pixel 7a
Geekbench ML Score
992
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | November 12 2024 10:09 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google Pixel 7a |
| Model ID | Google Pixel 7a |
| Motherboard | lynx |
| 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 @ 2.35 GHz |
| Cluster 3 | 2 Cores @ 2.85 GHz |
| Memory Information | |
|---|---|
| Size | 7.25 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
432
46.3 IPS |
|
|
Image Classification (F16)
|
100% |
508
54.5 IPS |
|
|
Image Classification (I8)
|
81% |
491
52.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
2010
12.4 IPS |
|
|
Image Segmentation (F16)
|
100% |
3670
22.7 IPS |
|
|
Image Segmentation (I8)
|
89% |
3751
23.2 IPS |
|
|
Pose Estimation (F32)
|
100% |
719
2.91 IPS |
|
|
Pose Estimation (F16)
|
0% |
2127
8.61 IPS |
|
|
Pose Estimation (I8)
|
0% |
1773
7.17 IPS |
|
|
Object Detection (F32)
|
100% |
601
21.1 IPS |
|
|
Object Detection (F16)
|
99% |
821
28.8 IPS |
|
|
Object Detection (I8)
|
54% |
788
27.6 IPS |
|
|
Face Detection (F32)
|
100% |
1372
15.8 IPS |
|
|
Face Detection (F16)
|
97% |
2481
28.5 IPS |
|
|
Face Detection (I8)
|
75% |
2149
24.7 IPS |
|
|
Text Classification (F32)
|
100% |
270
106.7 IPS |
|
|
Text Classification (F16)
|
46% |
299
118.1 IPS |
|
|
Machine Translation (F32)
|
100% |
683
105.2 IPS |
|
|
Machine Translation (F16)
|
100% |
684
105.4 IPS |
