---
title: gemma-4-e2b-it-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/gemma-4-e2b-it-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/gemma-4-e2b-it-4bit.md"
repository: mlx-community/gemma-4-e2b-it-4bit
last_updated: 2026-07-06
license: gemma
model_type:
  - gemma4
architectures:
  - Gemma4ForConditionalGeneration
base_model:
  - google/gemma-4-E2B-it
base_model_relation: quantized
parameters: 1.2B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 2454
stars: 2
tags:
  - mlx
  - mlx-vlm
  - gemma4
  - image-text-to-text
---

# gemma-4-e2b-it-4bit

> gemma-4-e2b-it-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/gemma-4-e2b-it-4bit

mlx-community/gemma-4-e2b-it-4bit 是 ModelScope 魔搭社区上的 1.2B 参数机器学习模型，采用 gemma 许可，基于 google/gemma-4-E2B-it 构建。

- **Repository**: mlx-community/gemma-4-e2b-it-4bit
- **License**: gemma
- **Parameters**: 1.2B
- **Base model**: google/gemma-4-E2B-it
- **Tags**: mlx, mlx-vlm, gemma4, image-text-to-text
- **Downloads**: 2454
- **Stars**: 2
- **Last updated**: 2026-07-06

Source: https://www.modelscope.cn/models/mlx-community/gemma-4-e2b-it-4bit

---

# mlx-community/gemma-4-e2b-it-4bit

MLX conversion of [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) for Apple silicon.

- Source revision: `70af34e20bd4b7a91f0de6b22675850c43922a03`
- Variant: `4bit`
- Converted with `mlx_vlm.convert` from the local `mlx-vlm` checkout.

## Usage

```bash
pip install mlx-vlm
python -m mlx_vlm.generate --model mlx-community/gemma-4-e2b-it-4bit --prompt "Describe this image." --image path/to/image.jpg
```