Qualcomm msmnile_gvmq for arm64
Geekbench ML Score
2393
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 19 2024 07:35 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)
|
11% |
2182
233.8 IPS |
|
|
Image Classification (F16)
|
3% |
3007
322.2 IPS |
|
|
Image Classification (I8)
|
4% |
2827
302.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
5527
34.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
9175
56.7 IPS |
|
|
Image Segmentation (I8)
|
89% |
9406
58.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
2727
11.0 IPS |
|
|
Pose Estimation (F16)
|
93% |
5209
21.1 IPS |
|
|
Pose Estimation (I8)
|
80% |
5187
21.0 IPS |
|
|
Object Detection (F32)
|
92% |
920
32.3 IPS |
|
|
Object Detection (F16)
|
98% |
1064
37.3 IPS |
|
|
Object Detection (I8)
|
48% |
1052
36.9 IPS |
|
|
Face Detection (F32)
|
84% |
3263
37.5 IPS |
|
|
Face Detection (F16)
|
75% |
5545
63.7 IPS |
|
|
Face Detection (I8)
|
61% |
5100
58.6 IPS |
|
|
Text Classification (F32)
|
46% |
715
282.7 IPS |
|
|
Text Classification (F16)
|
46% |
745
294.6 IPS |
|
|
Machine Translation (F32)
|
100% |
696
107.3 IPS |
|
|
Machine Translation (F16)
|
100% |
692
106.6 IPS |
