---
title: gemma-3n-E4B-it-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/gemma-3n-E4B-it-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/gemma-3n-E4B-it-bf16.md"
repository: mlx-community/gemma-3n-E4B-it-bf16
last_updated: 2025-07-13
license: gemma
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - gemma3n
architectures:
  - Gemma3nForConditionalGeneration
base_model:
  - google/gemma-3n-E4B
base_model_relation: finetune
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 230
stars: 0
tags:
  - automatic-speech-recognition
  - automatic-speech-translation
  - audio-text-to-text
  - video-text-to-text
  - mlx
---

# gemma-3n-E4B-it-bf16

> gemma-3n-E4B-it-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/gemma-3n-E4B-it-bf16 This model was converted to MLX format from google/gemma-3n-E4B-it using mlx-vlm version 0.3.1. Refer to the original model card for more details on the model. Use…

mlx-community/gemma-3n-E4B-it-bf16 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 gemma 许可，基于 google/gemma-3n-E4B 构建，可用 deploy_task vlm/text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/gemma-3n-E4B-it-bf16
- **License**: gemma
- **Tasks**: image-text-to-text
- **Base model**: google/gemma-3n-E4B
- **Inference backends**: deploy_task vlm/text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: automatic-speech-recognition, automatic-speech-translation, audio-text-to-text, video-text-to-text, mlx
- **Downloads**: 230
- **Stars**: 0
- **Last updated**: 2025-07-13

Source: https://www.modelscope.cn/models/mlx-community/gemma-3n-E4B-it-bf16

---

# mlx-community/gemma-3n-E4B-it-bf16
This model was converted to MLX format from [`google/gemma-3n-E4B-it`]() using mlx-vlm version **0.3.1**.
Refer to the [original model card](https://huggingface.co/google/gemma-3n-E4B-it) 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-3n-E4B-it-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```