Model comparison

MOSS-TTS-Local-Transformer-v1.5 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

MOSS-TTS-Local-Transformer-v1.5s2-pro
Parameters4.6B4.6B
Architecturemoss-audio-tokenizer-nanofish-speech
Layers36
Native context
Mixture of expertsnoyes, 1 experts
Quantizations published37
Smallest quantization5.56 GiB2.40 GiB
Q4_K_M3.32 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextMOSS-TTS-Local-Transformer-v1.5s2-proRatio
4,096
8,192
16,384
32,768
65,536
131,072