---
title: deepseek-vl2-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/deepseek-vl2-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/deepseek-vl2-8bit.md"
repository: mlx-community/deepseek-vl2-8bit
last_updated: 2025-02-06
license: other
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - deepseek_vl_v2
parameters: 7.8B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 927
stars: 0
tags:
  - mlx
---

# deepseek-vl2-8bit

> deepseek-vl2-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/deepseek-vl2-8bit This model was converted to MLX format from prince-canuma/deepseek-vl2 using mlx-vlm version 0.1.9. Refer to the original model card for more details on the model. Use with…

mlx-community/deepseek-vl2-8bit 是 ModelScope 魔搭社区上的 7.8B 参数image-text-to-text模型，采用 other 许可。

- **Repository**: mlx-community/deepseek-vl2-8bit
- **License**: other
- **Tasks**: image-text-to-text
- **Parameters**: 7.8B
- **Tags**: mlx
- **Downloads**: 927
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/deepseek-vl2-8bit

---

# mlx-community/deepseek-vl2-8bit
This model was converted to MLX format from [`prince-canuma/deepseek-vl2`]() using mlx-vlm version **0.1.9**.
Refer to the [original model card](https://huggingface.co/prince-canuma/deepseek-vl2) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/deepseek-vl2-8bit --max-tokens 100 --temp 0.0
```