---
title: Ming-3.0-audio-tiny-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Ming-3.0-audio-tiny-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Ming-3.0-audio-tiny-4bit.md"
repository: mlx-community/Ming-3.0-audio-tiny-4bit
last_updated: 2026-10-20
license: mit
model_type:
  - ming_v3_audio
architectures:
  - BailingMoeV3AudioForConditionalGeneration
base_model:
  - inclusionAI/Ming-3.0-audio-tiny
base_model_relation: quantized
parameters: 169.6M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 106
stars: 0
tags:
  - mlx
  - audio
---

# Ming-3.0-audio-tiny-4bit

> Ming-3.0-audio-tiny-4bit - mlx-community 在 ModelScope 开源的模型。Ming-3.0 Audio Tiny for MLX

mlx-community/Ming-3.0-audio-tiny-4bit 是 ModelScope 魔搭社区上的 169.6M 参数机器学习模型，采用 mit 许可，基于 inclusionAI/Ming-3.0-audio-tiny 构建。

- **Repository**: mlx-community/Ming-3.0-audio-tiny-4bit
- **License**: mit
- **Parameters**: 169.6M
- **Base model**: inclusionAI/Ming-3.0-audio-tiny
- **Tags**: mlx, audio
- **Downloads**: 106
- **Stars**: 0
- **Last updated**: 2026-10-20

Source: https://www.modelscope.cn/models/mlx-community/Ming-3.0-audio-tiny-4bit

---

# Ming-3.0 Audio Tiny for MLX

Converted from [inclusionAI/Ming-3.0-audio-tiny](https://huggingface.co/inclusionAI/Ming-3.0-audio-tiny).

English and Chinese audio understanding, transcription, text chat and spoken dialogue. `task='spoken_dialogue'` loads the bundled Talker lazily and produces 44.1 kHz audio. Only the thinker language backbone and text head are quantized; audio modules, routers and Talker remain floating-point. Speculative MTP decoding and streaming are not implemented. Reference speaker extraction uses the bundled native MLX CAMPPlus encoder. No ONNX packages are required.

```python
from mlx_audio.sts import load
model = load('dev/ming3/converted/Ming-3.0-audio-tiny-4bit', strict=True)
result = model.generate("speech.wav", task="audio_understanding",
                        text="Describe what you hear.")
print(result.text)
```

Offline inference on Apple Silicon using native MLX code. The tokenizer is loaded without executing remote code.