Qualcomm msmnile_gvmq for arm64
Geekbench ML Score
2341
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | September 19 2024 06:36 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Qualcomm msmnile_gvmq for arm64 |
| Model ID | Qualcomm msmnile_gvmq for arm64 |
| Motherboard | msmnile |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3403 revision 0 |
| Base Frequency | 2.59 GHz |
| Cluster 1 | 4 Cores @ 2.25 GHz |
| Cluster 2 | 4 Cores @ 2.59 GHz |
| Memory Information | |
|---|---|
| Size | 10.20 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
39% |
2173
232.8 IPS |
|
|
Image Classification (F16)
|
3% |
2812
301.3 IPS |
|
|
Image Classification (I8)
|
1% |
2794
299.4 IPS |
|
|
Image Segmentation (F32)
|
99% |
5514
34.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
9178
56.7 IPS |
|
|
Image Segmentation (I8)
|
89% |
9374
57.9 IPS |
|
|
Pose Estimation (F32)
|
20% |
2589
10.5 IPS |
|
|
Pose Estimation (F16)
|
33% |
4899
19.8 IPS |
|
|
Pose Estimation (I8)
|
33% |
4811
19.5 IPS |
|
|
Object Detection (F32)
|
88% |
922
32.4 IPS |
|
|
Object Detection (F16)
|
60% |
1066
37.4 IPS |
|
|
Object Detection (I8)
|
37% |
1064
37.3 IPS |
|
|
Face Detection (F32)
|
64% |
3246
37.3 IPS |
|
|
Face Detection (F16)
|
37% |
5370
61.7 IPS |
|
|
Face Detection (I8)
|
40% |
4959
57.0 IPS |
|
|
Text Classification (F32)
|
58% |
640
253.0 IPS |
|
|
Text Classification (F16)
|
46% |
742
293.5 IPS |
|
|
Machine Translation (F32)
|
100% |
703
108.3 IPS |
|
|
Machine Translation (F16)
|
100% |
702
108.3 IPS |
