Profile Job Results
Jobs
jgl3rd68g
Results Ready
Name
sam2_float_SAM2Decoder
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_embeddings: float32[1, 64, 64, 256]high_res_features1: float32[1, 256, 256, 32]high_res_features2: float32[1, 128, 128, 64]sparse_embedding: float32[1, 3, 256]Completion Time
1/10/2026, 7:33:49 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.41.0.251128145156_191518-auto
- QNN TfLite Delegate: v2.41.0.251128145156_191518-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
12.4 ms
Estimated Peak Memory Usage
0 ‑ 176 MB
Compute Units
NPU
806
| Stage | Time | Memory |
|---|---|---|
First App Load | 12.6 s | 201‑210 MB |
Subsequent App Load | 478 ms | 13‑190 MB |
Inference | 12.4 ms | 0‑176 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device