---
title: Laguna-XS.2-mxfp4
canonical_url: "https://www.modelscope.cn/models/mlx-community/Laguna-XS.2-mxfp4"
md_url: "https://www.modelscope.cn/models/mlx-community/Laguna-XS.2-mxfp4.md"
repository: mlx-community/Laguna-XS.2-mxfp4
last_updated: 2026-04-28
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - laguna
architectures:
  - LagunaForCausalLM
base_model:
  - poolside/Laguna-XS.2
base_model_relation: quantized
parameters: 6.3B
tensor_type:
  - U32
  - BF16
  - U8
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 12
stars: 0
tags:
  - laguna-xs.2
  - mlx
---

# Laguna-XS.2-mxfp4

> Laguna-XS.2-mxfp4 - mlx-community 在 ModelScope 开源的模型。mlx-community/Laguna-XS.2-mxfp4

mlx-community/Laguna-XS.2-mxfp4 是 ModelScope 魔搭社区上的 6.3B 参数text-generation模型，采用 apache-2.0 许可，基于 poolside/Laguna-XS.2 构建。

- **Repository**: mlx-community/Laguna-XS.2-mxfp4
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 6.3B
- **Base model**: poolside/Laguna-XS.2
- **Tags**: laguna-xs.2, mlx
- **Downloads**: 12
- **Stars**: 0
- **Last updated**: 2026-04-28

Source: https://www.modelscope.cn/models/mlx-community/Laguna-XS.2-mxfp4

---

# mlx-community/Laguna-XS.2-mxfp4

This model [mlx-community/Laguna-XS.2-mxfp4](https://huggingface.co/mlx-community/Laguna-XS.2-mxfp4) was
converted to MLX format from [poolside/Laguna-XS.2](https://huggingface.co/poolside/Laguna-XS.2)
using mlx-lm version **0.31.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Laguna-XS.2-mxfp4")

prompt = "hello"

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

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