Model comparison

FLUX.1-schnell vs FLUX.1-dev

At Q4_K_M, FLUX.1-schnell is the smaller download — 6,911,345,696 bytes against 6,931,817,760.

From the file· summed bytes, KV per layer

Side by side

FLUX.1-schnellFLUX.1-dev
Parameters11.9B11.9B
Architecturefluxflux
Layers
Native context
Mixture of expertsnono
Quantizations published3737
Smallest quantization3.73 GiB3.75 GiB
Q4_K_M6.44 GiB6.46 GiB
Licenceapache-2.0other

KV cache by context

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