Model comparison

Qwen3-TTS-Tokenizer-12Hz vs ced-base

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

From the file· summed bytes, KV per layer

Side by side

Qwen3-TTS-Tokenizer-12Hzced-base
Parameters171M86M
Architectureqwen3tts_tokenizerced
Layers
Native context
Mixture of expertsnono
Quantizations published13
Smallest quantization0.27 GiB0.12 GiB
Q4_K_M
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-TTS-Tokenizer-12Hzced-baseRatio
4,096
8,192
16,384
32,768
65,536
131,072