Model comparison

VieNeu-TTS vs neutts-air

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-TTSneutts-air
Parameters553M748M
Architectureqwen2qwen2
Layers2424
Native context32,76832,768
Mixture of expertsnono
Quantizations published16
Smallest quantization0.39 GiB0.43 GiB
Q4_K_M0.43 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextVieNeu-TTSneutts-airRatio
4,0960.05 GiB0.05 GiB1.00×
8,1920.09 GiB0.09 GiB1.00×
16,3840.19 GiB0.19 GiB1.00×
32,7680.38 GiB0.38 GiB1.00×
65,5360.75 GiB0.75 GiB1.00×
131,0721.50 GiB1.50 GiB1.00×