Profile Job Results
Jobs
jogkn3mvg
Results Ready
Name
riffusion_quantized_UNet_Quantized
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
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
10/3/2024, 11:30:21 PM
Versions
- QNN: v2.26.0.240827110523_99241
- QNN Backend API: 5.26.0
- QNN Core API: 2.19.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.10.01.0
Estimated Inference Time
128 ms
Estimated Peak Memory Usage
1 ‑ 2 MB
Compute Units
NPU
4932
Stage | Time | Memory |
---|---|---|
First App Load | 1.19 s | 2‑3 MB |
Subsequent App Load | 512 ms | 2‑4 MB |
Inference | 128 ms | 1‑2 MB |
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