Profile Job Results
Jobs
jp0l8rv2p
Results Ready
Name
segformer_base_w8a8
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 512, 512, 3]Completion Time
12/13/2025, 7:49:42 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.12.07.0
Estimated Inference Time
419 ms
Estimated Peak Memory Usage
1 ‑ 39 MB
Compute Units
CPU
310
GPU
256
NPU
44
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.27 s | 43‑45 MB |
Subsequent App Load | 3.10 s | 15‑17 MB |
Inference | 419 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