14:12
2026-08-26
forum.level1techs.com
large-language-models
Running qwen 3.6 / 3.8 on 3090+3080 over RPC?
A user running Qwen 3.8 27B on a 3090 reports that switching to ninfer, a Qwen-focused inference engine, doubled their token generation speed from 35-40 to 55-60 tokens per second. The user is conside…