Model comparison

ZONOS2 vs s2-pro

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

From the file· summed bytes, KV per layer

Side by side

ZONOS2s2-pro
Parameters4.6B
Architecturedacfish-speech
Layers36
Native context
Mixture of expertsnoyes, 1 experts
Quantizations published57
Smallest quantization4.58 GiB2.40 GiB
Q4_K_M3.32 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextZONOS2s2-proRatio
4,096
8,192
16,384
32,768
65,536
131,072