Model comparison

FLUX.1-Fill-dev vs FLUX.1-dev

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

From the file· summed bytes, KV per layer

Side by side

FLUX.1-Fill-devFLUX.1-dev
Parameters11.9B11.9B
Architecturefluxflux
Layers
Native context
Mixture of expertsnono
Quantizations published2537
Smallest quantization3.87 GiB3.75 GiB
Q4_K_M6.46 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
ContextFLUX.1-Fill-devFLUX.1-devRatio
4,096
8,192
16,384
32,768
65,536
131,072