---
title: Lingshu-7B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Lingshu-7B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Lingshu-7B-4bit.md"
repository: mlx-community/Lingshu-7B-4bit
last_updated: 2025-06-13
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen2_5_vl
architectures:
  - Qwen2_5_VLForConditionalGeneration
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 311
stars: 0
tags:
  - medical
  - multimodal
  - "report generation"
  - radiology
  - clinical-reasoning
  - MRI
  - CT
  - Histopathology
  - X-ray
  - Fundus
  - mlx
---

# Lingshu-7B-4bit

> Lingshu-7B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Lingshu-7B-4bit This model was converted to MLX format from lingshu-medical-mllm/Lingshu-7B using mlx-vlm version 0.1.27. Refer to the original model card for more details on the model. Use…

mlx-community/Lingshu-7B-4bit 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 mit 许可，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/Lingshu-7B-4bit
- **License**: mit
- **Tasks**: image-text-to-text
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: medical, multimodal, report generation, radiology, clinical-reasoning, MRI, CT, Histopathology, X-ray, Fundus, mlx
- **Downloads**: 311
- **Stars**: 0
- **Last updated**: 2025-06-13

Source: https://www.modelscope.cn/models/mlx-community/Lingshu-7B-4bit

---

# mlx-community/Lingshu-7B-4bit
This model was converted to MLX format from [`lingshu-medical-mllm/Lingshu-7B`]() using mlx-vlm version **0.1.27**.
Refer to the [original model card](https://huggingface.co/lingshu-medical-mllm/Lingshu-7B) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Lingshu-7B-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```