Qwen3-TTS-12Hz-0.6B-CustomVoice vs Kokoro-82M-v1.0-ONNX
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-TTS-12Hz-0.6B-CustomVoice | Kokoro-82M-v1.0-ONNX |
|---|---|---|
| Parameters | 910 M | — |
| Architecture | Qwen3TTSForConditionalGeneration | — |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 10 | 1 |
| Downloads 30d | 1,596,170 | 1,397,964 |
| Downloads all time | 4.9 M | 4.0 M |
| Quantizations on the Hub | SAFETENSORS | — |
| Gated | No | No |
| First seen on the Hub | 2026-01-21 | 2025-02-07 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
1.6 M1.3 M
Qwen3-TTS-12Hz-0.6B-CustomVoice
Kokoro-82M-v1.0-ONNX
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