Profile Job Results
Jobs
j5m30q7wg
Results Ready
Name
segformer_base_w8a8
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 512, 512, 3]Completion Time
11/29/2025, 6:06:00 PM
Options
--qairt_version latestVersions
- QAIRT: v2.40.0.251030114326_189385
- QNN Backend API: 5.40.0
- QNN Core API: 2.30.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
5.87 ms
Estimated Peak Memory Usage
1 ‑ 12 MB
Compute Units
NPU
335
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.42 s | 147‑149 MB |
Subsequent App Load | 1.40 s | 141‑143 MB |
Inference | 5.87 ms | 1‑12 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