PatternMapper's picture
Upload folder using huggingface_hub
3327940 verified
|
Raw
History Blame Contribute Delete
766 Bytes

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).