Profile Job Results
Jobs
jgo4n29k5
Results Ready
Name
albert_base_v2_hf
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]attention_masks: float32[1, 384]mask_indices: int32[1]Completion Time
7/4/2026, 7:19:09 PM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
22.0 ms
Estimated Peak Memory Usage
0 ‑ 13 MB
Compute Units
NPU
538
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.93 s | 244‑245 MB |
Subsequent App Load | 237 ms | 31‑52 MB |
Inference | 22.0 ms | 0‑13 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device