VoxCPM2 vs Qwen3-TTS-12Hz-1.7B-VoiceDesign

Specs, VRAM requirements and download trends — updated 22 October 2026.

openbmb · A · Open weights
Params
2.3 B
Context
—
30d
902 K
apache-2.0 · commercial OK
Qwen · B · Open weights
Params
1.9 B
Context
—
30d
431 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification VoxCPM2 Qwen3-TTS-12Hz-1.7B-VoiceDesign
Parameters 2.3 B 1.9 B
Architecture — Qwen3TTSForConditionalGeneration
Context length — —
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 30 —
Downloads 30d 901,936 431,164
Downloads all time 3.6 M 4.8 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-04-03 2026-01-21

Download trend

Daily snapshots, last 87 days (28 Jul – 22 Oct)

1.0 M332 K
VoxCPM2 Qwen3-TTS-12Hz-1.7B-VoiceDesign A overtook B on 29 Sep

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Qwen3-TTS-12Hz-1.7B-VoiceDesign · fp16 5.8 GB / 24 GB
✅ Runs comfortably
VoxCPM2 · fp16 5.9 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons