Clef is based on Qwen3.8-27B and Clef-flash is based on Qwen3.8-9B (edit: actually Qwen3.5-9B). So, similar in spirit to Kev by my understanding, but based on a newer model.

▲

NitpickLawyer 3 hours ago | parent | next [-]

> and Clef-flash is based on Qwen3.8-9B

There is no official qwen 3.8 9b

From the model card:

> Clef-Flash is post-trained from Qwen/Qwen3.5-9B. See Clef for the larger variant.

	▲	bityard 3 hours ago \| parent \| next [-]
		Thanks, I missed that. Fixed my comment.
	▲	ddarolfi 3 hours ago \| parent \| prev [-]
		It's based on Qwen3.5-9B, maybe a typo

▲

okpatil 3 hours ago | parent | prev [-]

Atom is 60M Param (around 133x to 400x smaller).

16ms latency. And locally run.

https://at0m.pienomial.com/

Why go big when you can go small ?

▲

kamranjon 2 hours ago | parent [-]

Cause it's not open?

	▲	okpatil 2 hours ago \| parent [-]
		Good point. To counter, most of the AI is not open. So is none of Microsoft Products. As long as they work, we keep using them.