Profile Job Results
Jobs
jvgdve9eg
Results Ready
Name
riffusion_quantized_UNet_Quantized
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_1
: uint16[1, 64, 64, 4]input_2
: uint16[1, 1280]input_3
: uint16[1, 77, 768]Completion Time
5/21/2024, 5:17:50 PM
Versions
- QNN: v2.22.0.240425235059_92863
- QNN Backend API: 5.22.0
- QNN Core API: 2.15.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.05.15.0
Estimated Inference Time
90.2 ms
Estimated Peak Memory Usage
0 ‑ 2 GB
Compute Units
NPU
4933
Stage | Time | Memory |
---|---|---|
First App Load | 470 ms | 1‑9 MB |
Subsequent App Load | 412 ms | 4‑13 MB |
Inference | 90.2 ms | 0‑2 GB |
QNN | Value |
---|---|
context_options.htp_options.performance_mode | BURST |
default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device