---
title: Gemma-SEA-LION-v4-4B-VL-mlx-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit.md"
repository: mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit
last_updated: 2026-03-10
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - gemma3
architectures:
  - Gemma3ForConditionalGeneration
base_model:
  - google/gemma-3-4b-it
base_model_relation: finetune
parameters: 989.1M
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
  - vi
  - id
  - th
  - fil
  - ta
  - ms
  - my
inference_backends:
  - "deploy_task vlm/text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 23
stars: 0
tags:
  - mlx
---

# Gemma-SEA-LION-v4-4B-VL-mlx-3bit

> Gemma-SEA-LION-v4-4B-VL-mlx-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit This model was converted to MLX format from aisingapore/Gemma-SEA-LION-v4-4B-VL using mlx-vlm version 0.3.12. Refer to the original model card…

mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit 是 ModelScope 魔搭社区上的 989.1M 参数image-text-to-text模型，采用 apache-2.0 许可，基于 google/gemma-3-4b-it 构建，可用 deploy_task vlm/text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 989.1M
- **Base model**: google/gemma-3-4b-it
- **Inference backends**: deploy_task vlm/text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 23
- **Stars**: 0
- **Last updated**: 2026-03-10

Source: https://www.modelscope.cn/models/mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit

---

# mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit
This model was converted to MLX format from [`aisingapore/Gemma-SEA-LION-v4-4B-VL`]() using mlx-vlm version **0.3.12**.
Refer to the [original model card](https://huggingface.co/aisingapore/Gemma-SEA-LION-v4-4B-VL) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Gemma-SEA-LION-v4-4B-VL-mlx-3bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```