Pura
Cached
Feed
Dashboard
My "4-bit" quant was 6.2 bits per weight — The Koleslaw Blog
koleslaw.ai
·
2026-08-03
·
by
Long Nguyen
·
generic
Nemotron's hidden dimension is 2688, which is not divisible by 256. That one fact quietly inflated a 4-bit quant by a third and cost a weekend.
My "4-bit" quant was 6.2 bits per weight — The Koleslaw Blog
koleslaw.ai
Comments (0)
No comments yet
Comment