Comment by ycui7 9 hours ago so qwen3.x-27b on hardware? or better deepseek-v4-flash on hardware . 2 comments ycui7 Reply ilaksh 9 hours ago 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 8 hours ago 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.
ilaksh 9 hours ago 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 8 hours ago 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.
mdp2021 8 hours ago 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.
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.
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.