Model comparison

stable-diffusion-3.5-large vs FLUX.2-klein-9B

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

stable-diffusion-3.5-largeFLUX.2-klein-9B
Parameters8.1B9.1B
Architectureflux
Layers
Native context
Mixture of expertsnono
Quantizations published1729
Smallest quantization4.44 GiB3.71 GiB
Q4_K_M4.68 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
Contextstable-diffusion-3.5-largeFLUX.2-klein-9BRatio
4,096
8,192
16,384
32,768
65,536
131,072