---
title: Qwen3-Omni-30B-A3B-Instruct-5bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit.md"
repository: mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit
last_updated: 2025-12-26
license: other
pipeline_tag: any-to-any
tasks:
  - any-to-any
model_type:
  - qwen3_omni_moe
architectures:
  - Qwen3OmniMoeForConditionalGeneration
parameters: 1.4B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 60
stars: 0
tags:
  - multimodal
  - mlx
---

# Qwen3-Omni-30B-A3B-Instruct-5bit

> Qwen3-Omni-30B-A3B-Instruct-5bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit This model was converted to MLX format from Qwen/Qwen3-Omni-30B-A3B-Instruct using mlx-vlm version 0.3.10. Refer to the original model card for…

mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit 是 ModelScope 魔搭社区上的 1.4B 参数any-to-any模型，采用 other 许可。

- **Repository**: mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit
- **License**: other
- **Tasks**: any-to-any
- **Parameters**: 1.4B
- **Tags**: multimodal, mlx
- **Downloads**: 60
- **Stars**: 0
- **Last updated**: 2025-12-26

Source: https://www.modelscope.cn/models/mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit

---

# mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit
This model was converted to MLX format from [`Qwen/Qwen3-Omni-30B-A3B-Instruct`]() using mlx-vlm version **0.3.10**.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/Qwen3-Omni-30B-A3B-Instruct-5bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```