Most companies are scaling models UP to get better performance.
Qwen went the opposite direction.

Their 3.5-Flash model uses linear attention + sparse MoE architecture.

Translation: You get near-frontier performance without needing a data center to run it. pic.twitter.com/rN6cXx8Ox0

— God of Prompt (@godofprompt) 14 mars 2026

Most companies are scaling models UP to get better performance.
Qwen went the opposite direction. Their 3.5-Flash model uses linear attention + sparse MoE architecture. Translation: You get near-frontier performance without needing a data center to run it.

→ View original post on X — @godofprompt