Profile Job Results
Jobs
jp4v07x8p
Results Ready
Name
sam2_w8a8_SAM2Encoder
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 1024, 1024, 3]unnorm_coords: uint8[1, 2, 2]labels: uint8[1, 2]Completion Time
1/10/2026, 7:48:46 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
1.32 s
Estimated Peak Memory Usage
102 ‑ 122 MB
Compute Units
CPU
644
GPU
85
| Stage | Time | Memory |
|---|---|---|
First App Load | 52.0 s | 36‑38 MB |
Subsequent App Load | 215 ms | 46‑49 MB |
Inference | 1.32 s | 102‑122 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| 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