Model comparison

VibeVoice-1.5B vs s2-pro

At Q4_K_M, VibeVoice-1.5B is the smaller download — 3,536,105,184 bytes against 3,566,165,088.

From the file· summed bytes, KV per layer

Side by side

VibeVoice-1.5Bs2-pro
Parameters2.7B4.6B
Architecturevibevoice-asrfish-speech
Layers36
Native context
Mixture of expertsnoyes, 1 experts
Quantizations published207
Smallest quantization1.76 GiB2.40 GiB
Q4_K_M3.29 GiB3.32 GiB
Licencemitother

KV cache by context

the term that decides long-context viability
ContextVibeVoice-1.5Bs2-proRatio
4,096
8,192
16,384
32,768
65,536
131,072