Profile Job Results
Jobs
jgkqzn4ng
Results Ready
Name
efficientformer
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
9/28/2025, 7:29:58 AM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
31.7 ms
Estimated Peak Memory Usage
0 ‑ 75 MB
Compute Units
GPU
144
NPU
56
CPU
5
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.31 s | 133‑135 MB |
Subsequent App Load | 1.95 s | 142‑144 MB |
Inference | 31.7 ms | 0‑75 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-dsp" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-hta" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device