---
title: idefics2-8b-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/idefics2-8b-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/idefics2-8b-4bit.md"
repository: mlx-community/idefics2-8b-4bit
last_updated: 2025-01-31
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - idefics2
architectures:
  - Idefics2ForConditionalGeneration
parameters: 1.3B
tensor_type:
  - F16
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 1008
stars: 0
tags:
  - multimodal
  - vision
  - image-text-to-text
  - mlx
---

# idefics2-8b-4bit

> idefics2-8b-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/idefics2-8b-4bit This model was converted to MLX format from HuggingFaceM4/idefics2-8b using mlx-vlm version 0.1.0. Refer to the original model card for more details on the model. Use with mlx

mlx-community/idefics2-8b-4bit 是 ModelScope 魔搭社区上的 1.3B 参数image-text-to-text模型，采用 apache-2.0 许可。

- **Repository**: mlx-community/idefics2-8b-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.3B
- **Tags**: multimodal, vision, image-text-to-text, mlx
- **Downloads**: 1008
- **Stars**: 0
- **Last updated**: 2025-01-31

Source: https://www.modelscope.cn/models/mlx-community/idefics2-8b-4bit

---

# mlx-community/idefics2-8b-4bit
This model was converted to MLX format from [`HuggingFaceM4/idefics2-8b`]() using mlx-vlm version **0.1.0**.
Refer to the [original model card](https://huggingface.co/HuggingFaceM4/idefics2-8b) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/idefics2-8b-4bit --max-tokens 100 --temp 0.0
```