Profile Job Results
Jobs
jp2w2em4p
Results Ready
Name
gemma_4_e4b_it_vision_encoder_gemma_4_e4b_it
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_position_ids: int32[1, 2520, 2]pixel_values: float32[1, 2520, 768]Completion Time
9/5/2026, 10:06:48 AM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Android: 16 (BQ2A.260305.002-BP2A.250705.008)
- Build ID: Pakala.LA.2.0.r1-00234-STD.PROD-3
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
1.60 s
Estimated Peak Memory Usage
7 ‑ 17 MB
Compute Units
NPU
1554
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.28 s | 1‑8 MB |
Subsequent App Load | 1.27 s | 1‑12 MB |
Inference | 1.60 s | 7‑17 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device