Model comparison

chatterbox vs Fun-CosyVoice3-0.5B-2512

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

From the file· summed bytes, KV per layer

Side by side

chatterboxFun-CosyVoice3-0.5B-2512
Parameters264M
Architecturechatterbox-s3gencosyvoice3-campplus
Layers
Native context
Mixture of expertsnono
Quantizations published373
Smallest quantization0.17 GiB0.34 GiB
Q4_K_M0.46 GiB
Licencemitapache-2.0

KV cache by context

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