---
license: apache-2.0
language:
- en
- zh
- ja
- ko
- fr
- de
- es
tags:
- speech
- tts
- mlx
- qwen3
library_name: mlx
base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
---

# Qwen3 TTS 12Hz 1.7B Base — MLX 8-bit

MLX 8-bit quantized conversion of [Qwen/Qwen3-TTS-12Hz-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base) for Apple Silicon inference.

## Usage

Used by [speech-swift](https://github.com/soniqo/speech-swift) `Qwen3TTS` module:

```swift
let model = try await Qwen3TTSModel.fromPretrained(
    modelId: "aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit"
)
let audio = try model.synthesize("Hello, world!")
```

```bash
audio speak "Hello, world!" --model 1.7b-8bit -o output.wav
```

## Model Details

- **Architecture**: Qwen3-TTS (Talker transformer + Code Predictor + Mimi speech tokenizer decoder)
- **Parameters**: 1.7B
- **Quantization**: 8-bit (MLX, talker + code predictor)
- **Size**: ~2.8 GB
- **Sample rate**: 24 kHz
- **Codec rate**: 12.5 Hz

## Variants

| Variant | Quantization | Size | Model ID |
|---------|-------------|------|----------|
| 0.6B 8-bit | 8-bit | ~1.3 GB | [aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit](https://huggingface.co/aufklarer/Qwen3-TTS-12Hz-0.6B-Base-MLX-8bit) |
| **1.7B 8-bit** | **8-bit** | **~2.8 GB** | **aufklarer/Qwen3-TTS-12Hz-1.7B-Base-MLX-8bit** |

---

---

- **Guide**: [soniqo.audio/guides/speak](https://soniqo.audio/guides/speak)
- **Docs**: [soniqo.audio](https://soniqo.audio)
- **GitHub**: [soniqo/speech-swift](https://github.com/soniqo/speech-swift)