Model comparison

FLUX.2-klein-9B vs Chroma

At Q4_K_M, FLUX.2-klein-9B is the smaller download — 5,027,783,648 bytes against 5,566,533,792.

From the file· summed bytes, KV per layer

Side by side

FLUX.2-klein-9BChroma
Parameters9.1B8.9B
Architecturefluxflux
Layers
Native context
Mixture of expertsnono
Quantizations published29273
Smallest quantization3.71 GiB3.99 GiB
Q4_K_M4.68 GiB5.18 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
ContextFLUX.2-klein-9BChromaRatio
4,096
8,192
16,384
32,768
65,536
131,072