---
title: Dia-1.6B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Dia-1.6B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Dia-1.6B-4bit.md"
repository: mlx-community/Dia-1.6B-4bit
last_updated: 2025-04-25
license: apache-2.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - nari-labs/Dia-1.6B
base_model_relation: quantized
parameters: 1.6B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 689
stars: 0
tags:
  - mlx
---

# Dia-1.6B-4bit

> Dia-1.6B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Dia-1.6B-4bit This model was converted to MLX format from mlx-community/Dia-1.6B using mlx-audio version 0.1.0. Refer to the original model card for more details on the model. Use with mlx

mlx-community/Dia-1.6B-4bit 是 ModelScope 魔搭社区上的 1.6B 参数text-to-speech模型，采用 apache-2.0 许可，基于 nari-labs/Dia-1.6B 构建。

- **Repository**: mlx-community/Dia-1.6B-4bit
- **License**: apache-2.0
- **Tasks**: text-to-speech
- **Parameters**: 1.6B
- **Base model**: nari-labs/Dia-1.6B
- **Tags**: mlx
- **Downloads**: 689
- **Stars**: 0
- **Last updated**: 2025-04-25

Source: https://www.modelscope.cn/models/mlx-community/Dia-1.6B-4bit

---

# mlx-community/Dia-1.6B-4bit
This model was converted to MLX format from [`mlx-community/Dia-1.6B`](https://huggingface.co/mlx-community/Dia-1.6B) using mlx-audio version **0.1.0**.
Refer to the [original model card](https://huggingface.co/mlx-community/Dia-1.6B) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-audio
```

```bash
python -m mlx_audio.tts.generate --model mlx-community/Dia-1.6B-4bit --text "Describe this image."
```