---
title: MiniCPM-o-4_5-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM-o-4_5-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM-o-4_5-4bit.md"
repository: mlx-community/MiniCPM-o-4_5-4bit
last_updated: 2026-03-06
license: apache-2.0
pipeline_tag: any-to-any
tasks:
  - any-to-any
model_type:
  - minicpmo
architectures:
  - MiniCPMO
parameters: 2.0B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 117
stars: 1
tags:
  - minicpm-o
  - minicpm-v
  - multimodal
  - full-duplex
  - mlx
---

# MiniCPM-o-4_5-4bit

> MiniCPM-o-4_5-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/MiniCPM-o-45-4bit This model was converted to MLX format from openbmb/MiniCPM-o-45 using mlx-vlm version 0.3.13. Refer to the original model card for more details on the model. Use with mlx

mlx-community/MiniCPM-o-4_5-4bit 是 ModelScope 魔搭社区上的 2.0B 参数any-to-any模型，采用 apache-2.0 许可，可用 deploy_task vlm、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/MiniCPM-o-4_5-4bit
- **License**: apache-2.0
- **Tasks**: any-to-any
- **Parameters**: 2.0B
- **Inference backends**: deploy_task vlm, sglang 0.5.2, vllm 0.9.2
- **Tags**: minicpm-o, minicpm-v, multimodal, full-duplex, mlx
- **Downloads**: 117
- **Stars**: 1
- **Last updated**: 2026-03-06

Source: https://www.modelscope.cn/models/mlx-community/MiniCPM-o-4_5-4bit

---

# mlx-community/MiniCPM-o-4_5-4bit
This model was converted to MLX format from [`openbmb/MiniCPM-o-4_5`]() using mlx-vlm version **0.3.13**.
Refer to the [original model card](https://huggingface.co/openbmb/MiniCPM-o-4_5) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/MiniCPM-o-4_5-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```