Qwen3-TTS-12Hz-0.6B-CustomVoice vs OmniVoice

Specs, VRAM requirements and download trends — updated 10 November 2026.

Qwen · A · Open weights
Params
910 M
Context
—
30d
734 K
apache-2.0 · commercial OK
k2-fsa · B · Open weights
Params
610 M
Context
—
30d
3.5 M

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-TTS-12Hz-0.6B-CustomVoice OmniVoice
Parameters 910 M 610 M
Architecture Qwen3TTSForConditionalGeneration OmniVoice
Context length — —
Licence apache-2.0 —
Commercial use Allowed Unknown
Languages 10 646
Downloads 30d 734,090 3,545,067
Downloads all time 8.2 M 13.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-01-21 2026-03-30

Download trend

Daily snapshots, last 90 days (13 Aug – 10 Nov)

3.5 M730 K
Qwen3-TTS-12Hz-0.6B-CustomVoice OmniVoice

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
✅ Runs comfortably
OmniVoice · fp16 4.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons