Profile Job Results
Jobs
jp1ew6zng
Results Ready
Name
unet_segmentation_w8a8
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 640, 1280, 3]Completion Time
10/25/2025, 4:10:29 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
3.16 s
Estimated Peak Memory Usage
0 ‑ 847 MB
Compute Units
NPU
41
| Stage | Time | Memory |
|---|---|---|
First App Load | 696 ms | 4‑5 MB |
Subsequent App Load | 319 ms | 3‑5 MB |
Inference | 3.16 s | 0‑847 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-dsp" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device