Profile Job Results
Jobs
jpr4ok30g
Results Ready
Name
lama_dilated
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
mask: float32[1, 512, 512, 1]image: float32[1, 512, 512, 3]Completion Time
4/5/2026, 6:31:41 PM
Versions
- QAIRT: v2.43.0.260127150333_193827
- QNN Backend API: 5.43.0
- QNN Core API: 2.32.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
52.3 ms
Estimated Peak Memory Usage
3 ‑ 473 MB
Compute Units
NPU
332
| Stage | Time | Memory |
|---|---|---|
First App Load | 14.4 s | 650‑657 MB |
Subsequent App Load | 198 ms | 1‑472 MB |
Inference | 52.3 ms | 3‑473 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device