Profile Job Results
Jobs
jpyoq3y05
Results Ready
Name
pi05_backbone
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
prefix_att_2d_masks: float32[1, 1, 968, 968]hidden_state: float32[1, 968, 2048]rope_emb_cos: float32[1, 968, 1, 128]rope_emb_sin: float32[1, 968, 1, 128]Completion Time
9/20/2026, 6:03:33 AM
Options
--qairt_version latestVersions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
431 ms
Estimated Peak Memory Usage
13 ‑ 15 MB
Compute Units
NPU
2507
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.97 s | 3‑5 MB |
Subsequent App Load | 914 ms | 2‑19 MB |
Inference | 431 ms | 13‑15 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







