Profile Job Results
Jobs
jp0mkoo2g
Results Ready
Name
funasr_conformer_en
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
feats: float32[1, 167, 560]Completion Time
9/19/2026, 10:05:14 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
48.5 ms
Estimated Peak Memory Usage
3 ‑ 335 MB
Compute Units
NPU
3287
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.48 min | 982 MB |
Subsequent App Load | 590 ms | 329‑332 MB |
Inference | 48.5 ms | 3‑335 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