Profile Job Results
Jobs
jprx7rz9p
Results Ready
Name
qwen3_vl_8b_instruct_vision_encoder_qwen3_vl_8b_instruct
Target Device
- Samsung Galaxy S25
- Android 15
- Snapdragon® 8 Elite for Galaxy | SM8750-AC
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: uint16[1024, 1536]position_ids_cos: uint16[1024, 36]position_ids_sin: uint16[1024, 36]full_attention_mask: uint16[1, 1024, 1024]window_attention_mask: float16[1, 1024, 1024]Completion Time
10/17/2026, 1:43:50 PM
Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Android: 15 (AP3A.240905.015.A2)
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
142 ms
Estimated Peak Memory Usage
2 ‑ 14 MB
Compute Units
NPU
1652
| Stage | Time | Memory |
|---|---|---|
First App Load | 358 ms | 2‑10 MB |
Subsequent App Load | 348 ms | 11‑20 MB |
Inference | 142 ms | 2‑14 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