---
license: mit
language:
- en
- zh
tags:
- text-generation
- agent
- long-context
- code
- mlx
library_name: mlx
base_model: XiaomiMiMo/MiMo-V2.5-Pro
pipeline_tag: text-generation
---

# kernelpool/MiMo-V2.5-Pro-6bit

This model [kernelpool/MiMo-V2.5-Pro-6bit](https://huggingface.co/kernelpool/MiMo-V2.5-Pro-6bit) was
converted to MLX format from [XiaomiMiMo/MiMo-V2.5-Pro](https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro)
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("kernelpool/MiMo-V2.5-Pro-6bit")

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)
```