Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

VLM Inference Latency on Qualcomm Snapdragon 8 Gen 3 SoC llama.cpp quantization

6.82VE Latency (ms/patch)

MobileVLM-336

6.75567.19037.6258.0597Dec 28, 2023
Updated 3d ago

Evaluation Results

MethodLinks
2023.12
6.8234,89234.9321.5418.51
2023.12
7.7731,37041.718.420.7
2023.12
7.9827,5308.957.2284.43
2023.12
8.2317,3475.360.25329.89
2023.12
8.4327,66018.3612.2133.1