XTTS-v2 vs Qwen3-TTS-12Hz-0.6B-CustomVoice
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | XTTS-v2 | Qwen3-TTS-12Hz-0.6B-CustomVoice |
|---|---|---|
| Parameters | — | 910 M |
| Architecture | — | Qwen3TTSForConditionalGeneration |
| Context length | — | — |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | 10 |
| Downloads 30d | 9,181,973 | 1,596,170 |
| Downloads all time | 111.6 M | 4.9 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-10-31 | 2026-01-21 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
9.3 M1.6 M
XTTS-v2
Qwen3-TTS-12Hz-0.6B-CustomVoice
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-TTS-12Hz-0.6B-CustomVoice · fp16
3.4 GB / 24 GB