Downloads · 30 days
318
37% of all-time downloads
Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
PowerBeef02/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit is a text-to-speech model from PowerBeef02. Use it when you need text read aloud. It is set up for mlx-audio. The card lists the license as apache-2.0.
Vocello production artifact. Derived from mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit at revision 41d3337e8b7f2843a75841595fc14e4b9a7a4b96 (itself an MLX conversion of the corresponding Qwen/Qwen3-TTS checkpoin…
All-time downloads
860
Public
Parameters
1.9B
3.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.8 GB · 100%
Parameter types
How the weights are stored.
U321.8B · 96%
Base models
Model card
From the Hugging Face model README
PowerBeef02/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
Vocello production artifact. Derived from
mlx-community/Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit
at revision 41d3337e8b7f2843a75841595fc14e4b9a7a4b96 (itself an MLX conversion of the
corresponding Qwen/Qwen3-TTS checkpoint), with one change:
the 622 MB BF16 talker.model.text_embedding tensor is quantized to affine 8-bit
(group size 64) by Vocello's pinned conversion tooling
(scripts/convert_text_embedding_8bit.py, python-mlx 0.32.0). Every other tensor is
byte-identical to the source revision.
Measured on the Vocello support floor (Mac mini M2 8 GB): about 278 MB less resident
memory and 292 MB less download per artifact at parity real-time factor, with clean
deterministic audio QC. Measurement details live in the
Vocello repository (benchmarks/OPTIMIZATION.md §N).
These files are consumed by Vocello's fail-closed model catalog, which pins this repository at an exact revision with per-file SHA-256 digests.
- Task
- Text-to-Speech
- Library
- mlx-audio
- Type
- qwen3_tts
- License
- apache-2.0
- Created
- Jul 26, 2026
- Updated
- Sep 14, 2026