local-llm7 min read
Running Qwen3.8–27B on an RTX 4090
Running Qwen3.8–27B on an RTX 4090 Testing a 27B model at roughly 100 tokens per second, with a local API for an agent to use. _Kwangju Shin (KJ)_ Could I run Qwen3.8–27B at around 100 tokens per …
By Kwangju Shin (KJ)Towards AI

Read the full story
Originally published by Towards AI on Oct 22, 2026.
Comments
Sign in to join the discussion.