---
title: llmjp-4-vl-9b-mlx-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/llmjp-4-vl-9b-mlx-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/llmjp-4-vl-9b-mlx-4bit.md"
repository: mlx-community/llmjp-4-vl-9b-mlx-4bit
last_updated: 2026-09-09
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - llmjpvl
architectures:
  - LLMjpVLModel
base_model:
  - llm-jp/llm-jp-4-vl-9b
base_model_relation: quantized
parameters: 1.8B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ja
downloads: 30
stars: 0
tags:
  - mlx
---

# llmjp-4-vl-9b-mlx-4bit

> llmjp-4-vl-9b-mlx-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/llm-jp-4-vl-9b-mlx-4bit

mlx-community/llmjp-4-vl-9b-mlx-4bit 是 ModelScope 魔搭社区上的 1.8B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 llm-jp/llm-jp-4-vl-9b 构建。

- **Repository**: mlx-community/llmjp-4-vl-9b-mlx-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.8B
- **Base model**: llm-jp/llm-jp-4-vl-9b
- **Tags**: mlx
- **Downloads**: 30
- **Stars**: 0
- **Last updated**: 2026-09-09

Source: https://www.modelscope.cn/models/mlx-community/llmjp-4-vl-9b-mlx-4bit

---

# mlx-community/llm-jp-4-vl-9b-mlx-4bit

This model was converted to MLX format from [`llm-jp/llm-jp-4-vl-9b`](https://huggingface.co/llm-jp/llm-jp-4-vl-9b)
using mlx-vlm version **0.6.8**.
Refer to the [original model card](https://huggingface.co/llm-jp/llm-jp-4-vl-9b) for more details on the model.

## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/llm-jp-4-vl-9b-mlx-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```