Model comparison

VieNeu-TTS-0.3B 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

VieNeu-TTS-0.3BFun-CosyVoice3-0.5B-2512
Parameters244M
Architectureqwen3cosyvoice3-campplus
Layers28
Native context4,096
Mixture of expertsnono
Quantizations published23
Smallest quantization0.19 GiB0.34 GiB
Q4_K_M
Licencecc-by-nc-4.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextVieNeu-TTS-0.3BFun-CosyVoice3-0.5B-2512Ratio
4,0960.11 GiB
8,1920.22 GiB
16,3840.44 GiB
32,7680.88 GiB
65,5361.75 GiB
131,0723.50 GiB