<![CDATA[Qwen 3.8 Flash Next on RTX 3090's]]>I FEEL like this is too good to be true, runs a patched vLLM on 2 RTX 3090's:
GitHub recipe
Numbers are absolutely insane.

Something more in-line with what I'd expect is what Minachist achieved:
HF discussion
Blog post

No AI used
]]>https://airigs.net/topic/9/qwen-3.8-flash-next-on-rtx-3090-sRSS for NodeMon, 02 Nov 2026 07:04:02 GMTMon, 28 Sep 2026 17:10:59 GMT60