Profile Job Results
Jobs
jgdd7lnlg
Results Ready
Name
melotts_es_encoder
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
sid: int32[1]bert: float32[1, 1024, 512]ja_bert: float32[1, 768, 512]x: int32[1, 512]tone: int32[1, 512]language: int32[1, 512]x_lengths: int32[1]noise_scale_w: float32[1]sdp_ratio: float32[1]length_scale: float32[1]Completion Time
9/19/2026, 10:14:18 AM
Options
--qairt_version latestVersions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
26.9 ms
Estimated Peak Memory Usage
4 ‑ 11 MB
Compute Units
NPU
833
| Stage | Time | Memory |
|---|---|---|
First App Load | 262 ms | 2‑3 MB |
Subsequent App Load | 193 ms | 2‑3 MB |
Inference | 26.9 ms | 4‑11 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