Qualcomm msmnile_gvmq for arm64
Geekbench ML Score
2401
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | September 20 2024 03:15 AM |
| Views | 3 |
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)
|
19% |
2158
231.2 IPS |
|
|
Image Classification (F16)
|
4% |
3033
324.9 IPS |
|
|
Image Classification (I8)
|
3% |
2662
285.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
5492
33.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
9167
56.6 IPS |
|
|
Image Segmentation (I8)
|
89% |
9400
58.1 IPS |
|
|
Pose Estimation (F32)
|
60% |
2725
11.0 IPS |
|
|
Pose Estimation (F16)
|
13% |
5182
21.0 IPS |
|
|
Pose Estimation (I8)
|
20% |
5194
21.0 IPS |
|
|
Object Detection (F32)
|
91% |
927
32.5 IPS |
|
|
Object Detection (F16)
|
84% |
1071
37.6 IPS |
|
|
Object Detection (I8)
|
32% |
1072
37.6 IPS |
|
|
Face Detection (F32)
|
51% |
3397
39.0 IPS |
|
|
Face Detection (F16)
|
71% |
5569
64.0 IPS |
|
|
Face Detection (I8)
|
54% |
5172
59.4 IPS |
|
|
Text Classification (F32)
|
46% |
705
278.8 IPS |
|
|
Text Classification (F16)
|
46% |
767
303.2 IPS |
|
|
Machine Translation (F32)
|
100% |
702
108.1 IPS |
|
|
Machine Translation (F16)
|
100% |
707
108.9 IPS |
