Profile Job Results
Jobs
j5wq3lq45
Results Ready
Name
sam2_w8a8_SAM2Encoder
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
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
10/25/2025, 7:20:13 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
1.72 s
Estimated Peak Memory Usage
70 ‑ 280 MB
Compute Units
CPU
644
GPU
85
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.58 min | 253‑263 MB |
Subsequent App Load | 1.48 min | 100‑312 MB |
Inference | 1.72 s | 70‑280 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