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

ilaksh · 2026-08-06T20:59:41 1786049981

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 · 2026-08-06T21:55:30 1786053330

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.