---
title: deepseek-vl-7b-chat-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/deepseek-vl-7b-chat-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/deepseek-vl-7b-chat-4bit.md"
repository: mlx-community/deepseek-vl-7b-chat-4bit
last_updated: 2024-12-26
license: other
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - multi_modality
architectures:
  - MultiModalityCausalLM
parameters: 1.2B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
downloads: 1059
stars: 1
tags:
  - mlx
---

# deepseek-vl-7b-chat-4bit

> deepseek-vl-7b-chat-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/deepseek-vl-7b-chat-4bit This model was converted to MLX format from deepseek-ai/deepseek-vl-7b-chat using mlx-vlm version 0.0.8. Refer to the original model card for more details on…

mlx-community/deepseek-vl-7b-chat-4bit 是 ModelScope 魔搭社区上的 1.2B 参数image-text-to-text模型，采用 other 许可，可用 deploy_task vlm/text、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/deepseek-vl-7b-chat-4bit
- **License**: other
- **Tasks**: image-text-to-text
- **Parameters**: 1.2B
- **Inference backends**: deploy_task vlm/text, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2
- **Tags**: mlx
- **Downloads**: 1059
- **Stars**: 1
- **Last updated**: 2024-12-26

Source: https://www.modelscope.cn/models/mlx-community/deepseek-vl-7b-chat-4bit

---

# mlx-community/deepseek-vl-7b-chat-4bit
This model was converted to MLX format from [`deepseek-ai/deepseek-vl-7b-chat`]() using mlx-vlm version **0.0.8**.
Refer to the [original model card](https://huggingface.co/deepseek-ai/deepseek-vl-1.3b-chat) 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-vl-7b-chat-4bit --max-tokens 100 --temp 0.0
```