Qualcomm msmnile_gvmq for arm64
Geekbench ML Score
2400
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 19 2024 08:10 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 | 24.56 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
4% |
2187
234.4 IPS |
|
|
Image Classification (F16)
|
3% |
3029
324.6 IPS |
|
|
Image Classification (I8)
|
6% |
2825
302.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
5498
34.0 IPS |
|
|
Image Segmentation (F16)
|
100% |
9192
56.8 IPS |
|
|
Image Segmentation (I8)
|
89% |
9394
58.0 IPS |
|
|
Pose Estimation (F32)
|
100% |
2728
11.0 IPS |
|
|
Pose Estimation (F16)
|
87% |
5214
21.1 IPS |
|
|
Pose Estimation (I8)
|
67% |
5209
21.1 IPS |
|
|
Object Detection (F32)
|
95% |
912
32.0 IPS |
|
|
Object Detection (F16)
|
87% |
1065
37.4 IPS |
|
|
Object Detection (I8)
|
48% |
1062
37.3 IPS |
|
|
Face Detection (F32)
|
93% |
3401
39.1 IPS |
|
|
Face Detection (F16)
|
71% |
5536
63.6 IPS |
|
|
Face Detection (I8)
|
51% |
5125
58.9 IPS |
|
|
Text Classification (F32)
|
46% |
716
283.2 IPS |
|
|
Text Classification (F16)
|
46% |
744
294.2 IPS |
|
|
Machine Translation (F32)
|
100% |
693
106.9 IPS |
|
|
Machine Translation (F16)
|
100% |
698
107.6 IPS |
