Alternatives to Qwen3-TTS-12Hz-0.6B-Base

Qwen3-TTS-12Hz-0.6B-Base alternatives

Qwen3-TTS-12Hz-0.6B-Base's smallest published quantization is 0.50 GiB. The models below do the same job with a different trade — less memory, comparable size, or a more permissive licence.

From the file· sizes from summed file bytes

Meaningfully smaller

under 70% of its smallest quantization
ModelParamsSmallestQuantsLicence
Ace-Step1.5160M0.04 GiB116other
VieNeu-TTS-0.3B244M0.19 GiB2cc-by-nc-4.0
Fun-CosyVoice3-0.5B-25120.34 GiB3apache-2.0
chatterbox264M0.17 GiB37mit
Kokoro-82M82M0.13 GiB4apache-2.0

Comparable in size

within ±40%, so a like-for-like swap
ModelParamsSmallestQuantsLicence
OmniVoice613M0.56 GiB7apache-2.0
neutts-air748M0.43 GiB6apache-2.0
VieNeu-TTS553M0.39 GiB1apache-2.0
VibeVoice-Realtime-0.5B1.0B0.65 GiB3mit

More permissively licensed

licences that allow commercial use
ModelParamsSmallestQuantsLicence
OmniVoice613M0.56 GiB7apache-2.0
orpheus-3b-0.1-ft3.8B0.91 GiB22apache-2.0
neutts-air748M0.43 GiB6apache-2.0
Fun-CosyVoice3-0.5B-25120.34 GiB3apache-2.0
VoxCPM22.3B1.57 GiB7apache-2.0
chatterbox264M0.17 GiB37mit
Kokoro-82M82M0.13 GiB4apache-2.0
VieNeu-TTS553M0.39 GiB1apache-2.0