Profile Job Results
Jobs
jp0zwxdn5
Results Ready
Name
mobilenet_v3_large_quantized
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
1/8/2025, 9:45:49 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
7.09 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
137
| Stage | Time | Memory |
|---|---|---|
First App Load | 322 ms | 1‑3 MB |
Subsequent App Load | 272 ms | 1‑4 MB |
Inference | 7.09 ms | 0‑3 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