Profile Job Results
Jobs
jp4e2rm2g
Results Ready
Name
qwen2_5_vl_7b_instruct_vision_encoder_qwen2_5_vl_7b_instruct
Target Device
- Samsung Galaxy S26
- Android 16
- Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: uint16[864, 1176]position_ids_cos: uint16[864, 40]position_ids_sin: uint16[864, 40]window_attention_mask: uint16[1, 864, 864]full_attention_mask: uint16[1, 864, 864]Completion Time
10/17/2026, 7:28:36 AM
Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Android: 16 (BP4A.251205.006)
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
120 ms
Estimated Peak Memory Usage
7 ‑ 15 MB
Compute Units
NPU
2071
| Stage | Time | Memory |
|---|---|---|
First App Load | 591 ms | 1‑11 MB |
Subsequent App Load | 386 ms | 1‑10 MB |
Inference | 120 ms | 7‑15 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 |
| default_graph_options.htp_options.enable_precision_compensation | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device