Alternatives to Qwen3-TTS-12Hz-1.7B-CustomVoice
Qwen3-TTS-12Hz-1.7B-CustomVoice alternatives
Qwen3-TTS-12Hz-1.7B-CustomVoice's smallest published quantization is 1.90 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
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| Ace-Step1.5 | 160M | 0.04 GiB | 116 | other |
| Qwen3-TTS-12Hz-0.6B-Base | 915M | 0.50 GiB | 10 | apache-2.0 |
| OmniVoice | 613M | 0.56 GiB | 7 | apache-2.0 |
| orpheus-3b-0.1-ft | 3.8B | 0.91 GiB | 22 | apache-2.0 |
| VieNeu-TTS-0.3B | 244M | 0.19 GiB | 2 | cc-by-nc-4.0 |
| neutts-air | 748M | 0.43 GiB | 6 | apache-2.0 |
| Fun-CosyVoice3-0.5B-2512 | — | 0.34 GiB | 3 | apache-2.0 |
| chatterbox | 264M | 0.17 GiB | 37 | mit |
Comparable in size
within ±40%, so a like-for-like swap
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| s2-proMoE | 4.6B | 2.40 GiB | 7 | other |
| VoxCPM2 | 2.3B | 1.57 GiB | 7 | apache-2.0 |
| csm-1b | 1.6B | 1.34 GiB | 3 | cc |
| orpheus-3b-0.1-pretrained | 3.8B | 1.40 GiB | 45 | apache-2.0 |
| Qwen3-TTS-12Hz-1.7B-VoiceDesign | 1.9B | 1.90 GiB | 2 | apache-2.0 |
| VibeVoice-1.5B | 2.7B | 1.76 GiB | 20 | mit |
| VoxCPM-0.5B | 728M | 2.45 GiB | 4 | — |
More permissively licensed
licences that allow commercial use
| Model | Params | Smallest | Quants | Licence |
|---|---|---|---|---|
| Qwen3-TTS-12Hz-0.6B-Base | 915M | 0.50 GiB | 10 | apache-2.0 |
| OmniVoice | 613M | 0.56 GiB | 7 | apache-2.0 |
| orpheus-3b-0.1-ft | 3.8B | 0.91 GiB | 22 | apache-2.0 |
| neutts-air | 748M | 0.43 GiB | 6 | apache-2.0 |
| Fun-CosyVoice3-0.5B-2512 | — | 0.34 GiB | 3 | apache-2.0 |
| VoxCPM2 | 2.3B | 1.57 GiB | 7 | apache-2.0 |
| chatterbox | 264M | 0.17 GiB | 37 | mit |
| Kokoro-82M | 82M | 0.13 GiB | 4 | apache-2.0 |