---
title: Gelato-30B-A3B-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Gelato-30B-A3B-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Gelato-30B-A3B-4bit.md"
repository: mlx-community/Gelato-30B-A3B-4bit
last_updated: 2025-11-17
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_vl_moe
architectures:
  - Qwen3VLMoeForConditionalGeneration
base_model:
  - mlfoundations/Gelato-30B-A3B
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 47
stars: 0
tags:
  - mlx
---

# Gelato-30B-A3B-4bit

> Gelato-30B-A3B-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Gelato-30B-A3B-4bit This model was converted to MLX format from mlfoundations/Gelato-30B-A3B using mlx-vlm version 0.3.6. Refer to the original model card for more details on the model. Use…

mlx-community/Gelato-30B-A3B-4bit 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 apache-2.0 许可，基于 mlfoundations/Gelato-30B-A3B 构建。

- **Repository**: mlx-community/Gelato-30B-A3B-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Base model**: mlfoundations/Gelato-30B-A3B
- **Tags**: mlx
- **Downloads**: 47
- **Stars**: 0
- **Last updated**: 2025-11-17

Source: https://www.modelscope.cn/models/mlx-community/Gelato-30B-A3B-4bit

---

# mlx-community/Gelato-30B-A3B-4bit
This model was converted to MLX format from [`mlfoundations/Gelato-30B-A3B`]() using mlx-vlm version **0.3.6**.
Refer to the [original model card](https://huggingface.co/mlfoundations/Gelato-30B-A3B) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Gelato-30B-A3B-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```