Model comparison

csm-1b 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

csm-1bs2-pro
Parameters1.6B4.6B
Architecturecsmfish-speech
Layers1636
Native context2,048
Mixture of expertsnoyes, 1 experts
Quantizations published37
Smallest quantization1.34 GiB2.40 GiB
Q4_K_M3.32 GiB
Licenceccother

KV cache by context

the term that decides long-context viability
Contextcsm-1bs2-proRatio
4,0960.13 GiB
8,1920.25 GiB
16,3840.50 GiB
32,7681.00 GiB
65,5362.00 GiB
131,0724.00 GiB