π“Ÿ host1.bitchan.one

𓀐 @VD~8Bn9i

⏱ 1d seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

>Really wish a modern 16-20B dense model existed. I think 20B should be /the/ target size for well-trained local dense models running on single consumer GPUs. It's a good size for 16GB (in 4-bit) and 24GB (in 6~8-bit) GPUs. More parameters could be added as Engram layers / PLE.⏱ 1d↩