Model comparison

Chroma vs FLUX.2-klein-9B

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

ChromaFLUX.2-klein-9B
Parameters8.9B9.1B
Architecturefluxflux
Layers
Native context
Mixture of expertsnono
Quantizations published27329
Smallest quantization3.99 GiB3.71 GiB
Q4_K_M5.18 GiB4.68 GiB
Licenceapache-2.0other

KV cache by context

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