Profile Job Results
Jobs
jp31480xg
Results Ready
Name
segformer_base
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 512, 512, 3]Completion Time
7/26/2025, 4:02:09 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
428 ms
Estimated Peak Memory Usage
1 ‑ 39 MB
Compute Units
CPU
308
GPU
255
NPU
43
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.50 s | 23‑25 MB |
Subsequent App Load | 3.29 s | 53‑56 MB |
Inference | 428 ms | 1‑39 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device