Model comparison

AuraFlow-v0.3 vs FLUX.2-klein-4B

At Q4_K_M, FLUX.2-klein-4B is the smaller download — 2,497,280,416 bytes against 4,047,070,496.

From the file· summed bytes, KV per layer

Side by side

AuraFlow-v0.3FLUX.2-klein-4B
Parameters6.9B3.9B
Architectureauraflux
Layers
Native context
Mixture of expertsnono
Quantizations published1421
Smallest quantization2.23 GiB1.70 GiB
Q4_K_M3.77 GiB2.33 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextAuraFlow-v0.3FLUX.2-klein-4BRatio
4,096
8,192
16,384
32,768
65,536
131,072