Profile Job Results
Jobs
jgk3m1yw5
Results Ready
Name
sam2_w8a8_SAM2Decoder
Target Device
- Snapdragon 8 Elite Gen 5 QRD
- Android 16
- Snapdragon® 8 Elite Gen 5 | SM8850
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_embeddings: uint8[1, 64, 64, 256]high_res_features1: uint8[1, 256, 256, 32]high_res_features2: uint8[1, 128, 128, 64]sparse_embedding: uint8[1, 3, 256]Completion Time
1/10/2026, 9:56:17 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.41.0.251128145156_191518
- QNN TfLite Delegate: v2.41.0.251128145156_191518
- Android: 16 (BQ2A.251016.001-BP2A.250605.031.A3)
- Build ID: Kaanapali.LA.1.0.r1-01040-STD.PROD-1
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
5.22 ms
Estimated Peak Memory Usage
0 ‑ 207 MB
Compute Units
NPU
830
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.76 s | 208‑214 MB |
Subsequent App Load | 111 ms | 9‑218 MB |
Inference | 5.22 ms | 0‑207 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| 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