Re:Qwen 3.8 27B on my laptop can interpret model weights, too
by Spivak on Tuesday November 03, 2026 @03:24PM
(#50357682)
This seems to be the inherent trade-off with smaller models. They can be just as "bright"
as their larger contemporaries but they necessarily can't encode as much knowledge.
[ Parent
| on HN ]
Re:Qwen 3.8 27B on my laptop can interpret model weights, too
by dcrazy on Tuesday November 03, 2026 @04:09PM
(#50358230)
I think this is what the n-gram table in Qwen 4 (and 3.8-Flash-Next) is for. We’ll see if it comes down to the 27b variant.
A RAG solution would make time to first token awful.
Re:Qwen 3.8 27B on my laptop can interpret model weights, too
by lnkdinsuxs on Tuesday November 03, 2026 @10:08PM
(#50361091)
> A RAG solution would make time to first token awful.
in your specific workflows, where specifically is the time to first token a dealbreaker? what's your typical target and what's a "no go"?
Re:Qwen 3.8 27B on my laptop can interpret model weights, too
by dcrazy on Tuesday November 03, 2026 @11:43PM
(#50361579)
I tend to use LLMs conversationally, often as search-and-summarize but also as a pair designer. I find it very difficult to operate in this mode if prefill takes more than, say, a dozen seconds. And that only gets to the reasoning output; depending of effort level it can be multiple minutes to get a reply in a freshly compacted context.