Qualcomm demos Qwen3-VL-32B running locally in FP16 via vLLM on Dragonfly

HowDevelop · x · 2026-11-19

Qualcomm's developer account showed Qwen3-VL-32B running locally on its Dragonfly platform in full FP16, using native PyTorch with vLLM through the open-source vLLM-QAIC plugin — a sign that mainstream inference stacks are extending to Qualcomm NPUs for on-device multimodal inference.

Original post →

More from Infra

Infra channel →