How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Qwen3.8-27B on a Lenovo laptop: run it on RTX Spark, watch it in Azure Monitor

calendar_today October 31, 2026 person Wuyi_Weng domain azure-container-apps

Updated October 30, 2026: the sample now runs vLLM 0.32 with async scheduling, 14% more decode steps a second on the code benchmark, and the memory bandwidth figure is corrected. See the update at the end. In an earlier post I served Qwen3.8-27B from an H100 in Azure .

open_in_new Read original post