Model comparison

stable-diffusion-v1-5 vs FLUX.2-klein-4B

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-v1-5FLUX.2-klein-4B
Parameters860M3.9B
Architectureflux
Layers
Native context
Mixture of expertsnono
Quantizations published721
Smallest quantization1.46 GiB1.70 GiB
Q4_K_M2.33 GiB
Licencecreativeml-openrail-mapache-2.0

KV cache by context

the term that decides long-context viability
Contextstable-diffusion-v1-5FLUX.2-klein-4BRatio
4,096
8,192
16,384
32,768
65,536
131,072
stable-diffusion-v1-5 vs FLUX.2-klein-4B — size, memory and hardware fit — ossmodeldb