---
title: MiniCPM-V-4.6-nvfp4
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM-V-4.6-nvfp4"
md_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM-V-4.6-nvfp4.md"
repository: mlx-community/MiniCPM-V-4.6-nvfp4
last_updated: 2026-05-14
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - minicpmv4_6
architectures:
  - MiniCPMV4_6ForConditionalGeneration
base_model:
  - openbmb/MiniCPM-V-4.6
base_model_relation: quantized
parameters: 1.1B
tensor_type:
  - BF16
  - U32
  - U8
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 33
stars: 0
tags:
  - minicpm-v
  - multimodal
  - "On-Device Model"
  - mlx
---

# MiniCPM-V-4.6-nvfp4

> MiniCPM-V-4.6-nvfp4 - mlx-community 在 ModelScope 开源的模型。mlx-community/MiniCPM-V-4.6-nvfp4

mlx-community/MiniCPM-V-4.6-nvfp4 是 ModelScope 魔搭社区上的 1.1B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 openbmb/MiniCPM-V-4.6 构建。

- **Repository**: mlx-community/MiniCPM-V-4.6-nvfp4
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.1B
- **Base model**: openbmb/MiniCPM-V-4.6
- **Tags**: minicpm-v, multimodal, On-Device Model, mlx
- **Downloads**: 33
- **Stars**: 0
- **Last updated**: 2026-05-14

Source: https://www.modelscope.cn/models/mlx-community/MiniCPM-V-4.6-nvfp4

---

# mlx-community/MiniCPM-V-4.6-nvfp4

This model was converted to MLX format from [`openbmb/MiniCPM-V-4.6`](https://huggingface.co/openbmb/MiniCPM-V-4.6)
using mlx-vlm version **0.5.0**.
Refer to the [original model card](https://huggingface.co/openbmb/MiniCPM-V-4.6) 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-V-4.6-nvfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```