---
title: MiniMax-M2-REAP-139B-A10B-mxfp4
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4"
md_url: "https://www.modelscope.cn/models/mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4.md"
repository: mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4
last_updated: 2026-01-04
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - minimax_m2
architectures:
  - MiniMaxM2ForCausalLM
base_model:
  - cerebras/MiniMax-M2-REAP-139B-A10B
base_model_relation: quantized
parameters: 10.5B
tensor_type:
  - U32
  - BF16
  - U8
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 32
stars: 0
tags:
  - minimax
  - MOE
  - pruning
  - compression
  - mlx
---

# MiniMax-M2-REAP-139B-A10B-mxfp4

> MiniMax-M2-REAP-139B-A10B-mxfp4 - mlx-community 在 ModelScope 开源的模型。mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4

mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4 是 ModelScope 魔搭社区上的 10.5B 参数text-generation模型，采用 other 许可，基于 cerebras/MiniMax-M2-REAP-139B-A10B 构建。

- **Repository**: mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 10.5B
- **Base model**: cerebras/MiniMax-M2-REAP-139B-A10B
- **Tags**: minimax, MOE, pruning, compression, mlx
- **Downloads**: 32
- **Stars**: 0
- **Last updated**: 2026-01-04

Source: https://www.modelscope.cn/models/mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4

---

# mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4

This model [mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4](https://huggingface.co/mlx-community/MiniMax-M2-REAP-139B-A10B-mxfp4) was
converted to MLX format from [cerebras/MiniMax-M2-REAP-139B-A10B](https://huggingface.co/cerebras/MiniMax-M2-REAP-139B-A10B)
using mlx-lm version **0.30.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniMax-M2-REAP-139B-A10B-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)
```