so qwen3.x-27b on hardware? or better deepseek-v4-flash on hardware .

I wrote them an email asking for PrismML Bonsai 27b Ternary which is like 6b or something crazy small and would be a lot easier for them to do initially.

	▲	mdp2021 an hour ago \| parent [-]
		They were specializing their forthcoming system on 4-bit FP - which I understand is a structural decision. Bonsai Ternary (1.7bits/weight) is a compromise, compromise that has to make sense in the context - efficient when translated into transistors.