Profile Job Results
Jobs
jp16nnx75
Results Ready
Name
melotts_en_flow
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
attn_squeezed: uint16[1, 1536, 512]logs_p: uint16[1, 192, 512]noise_scale: uint16[1]m_p: uint16[1, 192, 512]y_mask: uint16[1, 1, 1536]g: uint16[1, 256, 1]Completion Time
8/8/2026, 9:48:23 AM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
155 ms
Estimated Peak Memory Usage
2 ‑ 6 MB
Compute Units
NPU
763
| Stage | Time | Memory |
|---|---|---|
First App Load | 301 ms | 3‑4 MB |
Subsequent App Load | 282 ms | 1‑2 MB |
Inference | 155 ms | 2‑6 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