Model comparison

Fun-CosyVoice3-0.5B-2512 vs chatterbox

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

From the file· summed bytes, KV per layer

Side by side

Fun-CosyVoice3-0.5B-2512chatterbox
Parameters264M
Architecturecosyvoice3-camppluschatterbox-s3gen
Layers
Native context
Mixture of expertsnono
Quantizations published337
Smallest quantization0.34 GiB0.17 GiB
Q4_K_M0.46 GiB
Licenceapache-2.0mit

KV cache by context

the term that decides long-context viability
ContextFun-CosyVoice3-0.5B-2512chatterboxRatio
4,096
8,192
16,384
32,768
65,536
131,072