---
title: Ming-3.0-audio-tiny-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Ming-3.0-audio-tiny-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Ming-3.0-audio-tiny-bf16.md"
repository: mlx-community/Ming-3.0-audio-tiny-bf16
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: finetune
parameters: 565.6M
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 84
stars: 0
tags:
  - bf16
  - mlx
  - audio
---

# Ming-3.0-audio-tiny-bf16

> Ming-3.0-audio-tiny-bf16 - mlx-community 在 ModelScope 开源的模型。Ming-3.0 Audio Tiny for MLX

mlx-community/Ming-3.0-audio-tiny-bf16 是 ModelScope 魔搭社区上的 565.6M 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-bf16
- **License**: mit
- **Parameters**: 565.6M
- **Base model**: inclusionAI/Ming-3.0-audio-tiny
- **Tags**: bf16, mlx, audio
- **Downloads**: 84
- **Stars**: 0
- **Last updated**: 2026-10-20

Source: https://www.modelscope.cn/models/mlx-community/Ming-3.0-audio-tiny-bf16

---

# 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. The Thinker, audio encoder, Talker and audio VAE use BF16 weights. Speculative MTP decoding and streaming are not implemented. Reference speaker extraction uses the bundled native MLX CAMPPlus encoder. Its weights retain FP32 precision. No ONNX packages are required.

```python
from mlx_audio.sts import load
model = load('mlx-community/Ming-3.0-audio-tiny-bf16', 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.

Source checkpoint revision: `7cbe4a75c979f6ea48f1ee31998eb02bd7012233`.

This export includes all weights and tokenizers needed for its supported tasks. The native CAMPPlus weights are bundled under `talker/speaker_encoder`; their Apache-2.0 license and attribution accompany the weights. The complete Talker, its text tokenizer and audio VAE are included under `talker/`. No separate model downloads or ONNX packages are required. Use an MLX Audio version with Ming Tiny support.

The example repository name above may be replaced with the local export directory or your uploaded repository ID.

Validation: strictly reloaded from a relocated directory with an empty Hugging Face cache, network access blocked and ONNX packages absent. See `validation.json` for the tested tasks and weight inventory. `SHA256SUMS` covers all package files.