Profile Job Results
Jobs
jgjqr6ze5
Results Ready
Name
whisper_large_v3_turbo_quantized_decoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 1]k_cache_cross_0: uint8[20, 1, 64, 1500]k_cache_cross_1: uint8[20, 1, 64, 1500]k_cache_cross_2: uint8[20, 1, 64, 1500]k_cache_cross_3: uint8[20, 1, 64, 1500]k_cache_self_0_in: uint8[20, 1, 64, 199]k_cache_self_1_in: uint8[20, 1, 64, 199]k_cache_self_2_in: uint8[20, 1, 64, 199]k_cache_self_3_in: uint8[20, 1, 64, 199]position_ids: int32[1]v_cache_cross_0: uint8[20, 1, 1500, 64]v_cache_cross_1: uint8[20, 1, 1500, 64]v_cache_cross_2: uint8[20, 1, 1500, 64]v_cache_cross_3: uint8[20, 1, 1500, 64]v_cache_self_0_in: uint8[20, 1, 199, 64]v_cache_self_1_in: uint8[20, 1, 199, 64]v_cache_self_2_in: uint8[20, 1, 199, 64]v_cache_self_3_in: uint8[20, 1, 199, 64]attention_mask: uint16[1, 1, 1, 200]Completion Time
8/8/2026, 11:37:03 AM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
6.47 ms
Estimated Peak Memory Usage
14 ‑ 34 MB
Compute Units
NPU
1533
| Stage | Time | Memory |
|---|---|---|
First App Load | 265 ms | 2 MB |
Subsequent App Load | 285 ms | 3‑4 MB |
Inference | 6.47 ms | 14‑34 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