AI News HubLIVE
In-site rewrite1 min read

Show HN: Qwen3.8-27B API, 140 tok/s on one GPU

A developer on Hacker News showcases a Qwen3.8-27B API service, claiming 140 tokens per second on a single GPU.

SourceHacker News AIAuthor: anotherCodder

sign in · tiyuvta inference

Skip to content