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.
More from Infra
- 19 Core Concepts of AI System Design: From KV Cache to Multi-Agent Systems — blaizedsouza · 2026-11-19
- Swapping two used RTX 3090s for two Radeon R9700s: is ROCm ready for local inference? — Pear_Virtual · 2026-11-19
- Hugging Face's open-source nudge: 100GB private storage vs ~7TB for public data — RisingSayak · 2026-11-19
- Dev ports MiniMax H3 to Swift, cuts 480p video gen to ~4 min on a 16GB M1 MacBook — Lokoto123 · 2026-11-19
- Databricks explains LTAP: the lake is the database's storage, killing the CDC pipeline — matei_zaharia · 2026-11-19
- Solo dev cuts sandbox cold-start to 0.45s, sleeping VMs cost 1¢/month — emilahlback · 2026-11-19