Profile Job Results
Jobs
jp8e8vmxp
Results Ready
Name
grootn15_dit
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
actions: float32[1, 16, 32]vlm_proj_keys_7: float32[1, 32, 384, 48]vlm_proj_keys_6: float32[1, 32, 384, 48]vlm_proj_keys_5: float32[1, 32, 384, 48]vlm_proj_keys_4: float32[1, 32, 384, 48]vlm_proj_keys_3: float32[1, 32, 384, 48]vlm_proj_keys_2: float32[1, 32, 384, 48]vlm_proj_keys_1: float32[1, 32, 384, 48]vlm_proj_keys_0: float32[1, 32, 384, 48]state: float32[1, 1, 64]cross_attention_mask: float32[1, 32, 49, 384]vlm_proj_values_0: float32[1, 32, 384, 48]vlm_proj_values_1: float32[1, 32, 384, 48]vlm_proj_values_2: float32[1, 32, 384, 48]vlm_proj_values_3: float32[1, 32, 384, 48]vlm_proj_values_4: float32[1, 32, 384, 48]vlm_proj_values_5: float32[1, 32, 384, 48]vlm_proj_values_6: float32[1, 32, 384, 48]vlm_proj_values_7: float32[1, 32, 384, 48]Completion Time
9/20/2026, 4:20:49 AM
Options
--qairt_version latestVersions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
46.4 ms
Estimated Peak Memory Usage
39 ‑ 41 MB
Compute Units
NPU
2142
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.56 s | 2‑4 MB |
Subsequent App Load | 527 ms | 1‑3 MB |
Inference | 46.4 ms | 39‑41 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