Qwen3-TTS-12Hz-0.6B-CustomVoice
Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.
Params
910 M
Context
—
Downloads 30d
734 K
Likes
211
Download history
daily snapshots · 106 days
▲ 317 K in the last 30 days (30.2%)
1.0 M730 K
Oct 12Oct 22Nov 1Nov 10
1.5 M730 K
Aug 13Sep 12Oct 12Nov 10
1.6 M730 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 2.5 GB | 3.4 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- Qwen3TTSForConditionalGeneration
- Parameters
- 910 M
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-01-21
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-to-speech model
Popular comparisons
Appears in