---
title: EvoCUA-8B-20260105-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/EvoCUA-8B-20260105-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/EvoCUA-8B-20260105-8bit.md"
repository: mlx-community/EvoCUA-8B-20260105-8bit
last_updated: 2026-01-27
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_vl
architectures:
  - Qwen3VLForConditionalGeneration
base_model:
  - Qwen/Qwen3-VL-32B
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 21
stars: 0
tags:
  - computer-use
  - gui-agent
  - multimodal
  - osworld
  - mlx
---

# EvoCUA-8B-20260105-8bit

> EvoCUA-8B-20260105-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/EvoCUA-8B-20260105-8bit This model was converted to MLX format from meituan/EvoCUA-8B-20260105 using mlx-vlm version 0.3.9. Refer to the original model card for more details on the…

mlx-community/EvoCUA-8B-20260105-8bit 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 apache-2.0 许可，基于 Qwen/Qwen3-VL-32B 构建。

- **Repository**: mlx-community/EvoCUA-8B-20260105-8bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Base model**: Qwen/Qwen3-VL-32B
- **Tags**: computer-use, gui-agent, multimodal, osworld, mlx
- **Downloads**: 21
- **Stars**: 0
- **Last updated**: 2026-01-27

Source: https://www.modelscope.cn/models/mlx-community/EvoCUA-8B-20260105-8bit

---

# mlx-community/EvoCUA-8B-20260105-8bit
This model was converted to MLX format from [`meituan/EvoCUA-8B-20260105`]() using mlx-vlm version **0.3.9**.
Refer to the [original model card](https://huggingface.co/meituan/EvoCUA-8B-20260105) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/EvoCUA-8B-20260105-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```