Profile Job Results
Jobs
jz57o3wng
Results Ready
Name
stable_diffusion_v2_1_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
latent: uint16[1, 64, 64, 4]time_emb: uint16[1, 1280]text_emb: uint16[1, 77, 1024]Completion Time
8/16/2024, 8:15:44 PM
Versions
- QNN: v2.24.0.240626131148_96320
- QNN Backend API: 5.24.0
- QNN Core API: 2.17.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.12.0
Estimated Inference Time
72.6 ms
Estimated Peak Memory Usage
0 ‑ 8 MB
Compute Units
NPU
6361
| Stage | Time | Memory |
|---|---|---|
First App Load | 408 ms | 2‑9 MB |
Subsequent App Load | 387 ms | 1‑10 MB |
Inference | 72.6 ms | 0‑8 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