PrismML · Text-to-Image

Bonsai Image 4B

1-bit and ternary compressed variants of a 4B-class diffusion transformer (modified FLUX.2 Klein 4B) — memory drops from 7.75GB to 0.93GB (1-bit) or 1.21GB (ternary), up to 8.3× reduction. Retains 88% / 95% of FLUX.2 Klein 4B quality; generates 512² in ~9.4s on iPhone 17 Pro Max, ~6s on M4 Pro. Apache 2.0.