Downloads · 30 days
4
11% of all-time downloads
Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit
PatternMapper/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit
Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit is a machine learning model from PatternMapper. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
An 8-bit quantized MLX conversion of Qwen/Qwen3-TTS-12Hz-1.7B-Base.
All-time downloads
37
Public
Parameters
825M
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
Parameter types
How the weights are stored.
BF16441M · 53%
Model card
From the Hugging Face model README
Qwen3-TTS-12Hz-1.7B-Base — MLX 8-bit
An 8-bit quantized MLX conversion of Qwen/Qwen3-TTS-12Hz-1.7B-Base.
Details
- Original model: Qwen3-TTS-12Hz-1.7B-Base
- Quantization: 8-bit affine (group size 64)
- Framework: MLX
- Converted with: mlx-audio
Usage
from mlx_audio.tts import TTS
tts = TTS("PatternMapper/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit")
audio = tts.generate(text="Hello, world!")
Or with the mlx-audio CLI:
mlx_audio.tts.generate --model PatternMapper/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit --text "Hello, world!"
License
Apache 2.0 (same as the original model).
- Type
- qwen3_tts
- Created
- Feb 26, 2026
- Updated
- Feb 26, 2026