audio.cpp-gguf vs Qwen3-TTS-12Hz-1.7B-VoiceDesign

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

audio-cpp · A · Open weights
Params
—
Context
—
30d
6.6 M
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 audio.cpp-gguf Qwen3-TTS-12Hz-1.7B-VoiceDesign
Parameters — 1.9 B
Architecture — Qwen3TTSForConditionalGeneration
Context length — —
Licence other apache-2.0
Commercial use Unknown Allowed
Languages — —
Downloads 30d 6,584,182 431,164
Downloads all time 12.2 M 4.8 M
Quantizations on the Hub GGUF, SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-07-14 2026-01-21

Download trend

Daily snapshots, last 66 days (18 Aug – 22 Oct)

6.6 M332 K
audio.cpp-gguf Qwen3-TTS-12Hz-1.7B-VoiceDesign

VRAM side by side

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

audio.cpp-gguf · fp16 1.6 GB / 24 GB
✅ Runs comfortably
audio.cpp-gguf · Q4_0 4.7 GB / 24 GB
✅ Runs comfortably
Qwen3-TTS-12Hz-1.7B-VoiceDesign · fp16 5.8 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons