Profile Job Results
Jobs
jgn31mvk5
Results Ready
Name
sam2_w8a8_SAM2Encoder
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
Target Model
Input Specs
image: uint8[1, 1024, 1024, 3]unnorm_coords: uint8[1, 2, 2]labels: uint8[1, 2]Completion Time
12/3/2025, 7:30:35 AM
Versions
- TensorFlow Lite: 2.17.0
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
1.81 s
Estimated Peak Memory Usage
94 ‑ 344 MB
Compute Units
CPU
644
GPU
85
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.39 min | 307‑308 MB |
Subsequent App Load | 210 ms | 154‑155 MB |
Inference | 1.81 s | 94‑344 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