Profile Job Results
Jobs
jglxk8qeg
Results Ready
Name
sam2_encoder
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 1024, 1024, 3]unnorm_coords: uint8[1, 2, 2]labels: uint8[1, 2]Completion Time
8/22/2026, 11:45:54 PM
Versions
- Lite RT: 1.4.5
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
1.74 s
Estimated Peak Memory Usage
78 ‑ 340 MB
Compute Units
CPU
610
GPU
79
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.45 min | 385‑386 MB |
Subsequent App Load | 192 ms | 42‑43 MB |
Inference | 1.74 s | 78‑340 MB |
| Lite RT | 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