---
title: gemma-3n-E4B-it-text-4bit-dwq
canonical_url: "https://www.modelscope.ai/models/RealmSky/gemma-3n-E4B-it-text-4bit-dwq"
md_url: "https://www.modelscope.ai/models/RealmSky/gemma-3n-E4B-it-text-4bit-dwq.md"
repository: RealmSky/gemma-3n-E4B-it-text-4bit-dwq
last_updated: 2025-09-05
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gemma3n
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 9
stars: 0
---

# gemma-3n-E4B-it-text-4bit-dwq

> gemma-3n-E4B-it-text-4bit-dwq - An open-source model by RealmSky on ModelScope. mlx-community/gemma-3n-E4B-it-text-4bit-dwq

- **Repository**: RealmSky/gemma-3n-E4B-it-text-4bit-dwq
- **Tasks**: text-generation
- **Downloads**: 9
- **Stars**: 0
- **Last updated**: 2025-09-05

Source: https://www.modelscope.ai/models/RealmSky/gemma-3n-E4B-it-text-4bit-dwq

---

# mlx-community/gemma-3n-E4B-it-text-4bit-dwq

This model [mlx-community/gemma-3n-E4B-it-text-4bit-dwq](https://huggingface.co/mlx-community/gemma-3n-E4B-it-text-4bit-dwq) was
converted to MLX format from [google/gemma-3n-E4B-it](https://huggingface.co/google/gemma-3n-E4B-it)
using mlx-lm version **0.26.0**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-3n-E4B-it-text-4bit-dwq")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```