Model comparison

HunyuanImage-2.1 vs FLUX.2-klein-9B

At Q4_K_M, FLUX.2-klein-9B is the smaller download — 5,027,783,648 bytes against 9,236,273,920.

From the file· summed bytes, KV per layer

Side by side

HunyuanImage-2.1FLUX.2-klein-9B
Parameters17.5B9.1B
Architecturepigflux
Layers
Native context
Mixture of expertsnono
Quantizations published5029
Smallest quantization5.26 GiB3.71 GiB
Q4_K_M8.60 GiB4.68 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
ContextHunyuanImage-2.1FLUX.2-klein-9BRatio
4,096
8,192
16,384
32,768
65,536
131,072