---
title: aya-vision-32b-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/aya-vision-32b-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/aya-vision-32b-3bit.md"
repository: mlx-community/aya-vision-32b-3bit
last_updated: 2025-03-05
license: cc-by-nc-4.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - aya_vision
architectures:
  - AyaVisionForConditionalGeneration
parameters: 4.5B
tensor_type:
  - U32
  - F16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ja
  - ko
  - zh
  - ar
  - el
  - fa
  - pl
  - id
  - cs
  - he
  - hi
  - nl
  - ro
  - ru
  - tr
  - uk
  - vi
inference_backends:
  - "deploy_task vlm/text/emb"
  - "vllm 0.9.2"
downloads: 554
stars: 0
tags:
  - mlx
---

# aya-vision-32b-3bit

> aya-vision-32b-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/aya-vision-32b-3bit This model was converted to MLX format from CohereForAI/aya-vision-32b using mlx-vlm version 0.1.15. Refer to the original model card for more details on the model. Use…

mlx-community/aya-vision-32b-3bit 是 ModelScope 魔搭社区上的 4.5B 参数image-text-to-text模型，采用 cc-by-nc-4.0 许可，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/aya-vision-32b-3bit
- **License**: cc-by-nc-4.0
- **Tasks**: image-text-to-text
- **Parameters**: 4.5B
- **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 554
- **Stars**: 0
- **Last updated**: 2025-03-05

Source: https://www.modelscope.cn/models/mlx-community/aya-vision-32b-3bit

---

# mlx-community/aya-vision-32b-3bit
This model was converted to MLX format from [`CohereForAI/aya-vision-32b`]() using mlx-vlm version **0.1.15**.
Refer to the [original model card](https://huggingface.co/CohereForAI/aya-vision-32b) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/aya-vision-32b-3bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```