---
library_name: mlx
license: apache-2.0
pipeline_tag: text-generation
tags:
- looped-language-model
- reasoning
- recurrent-depth
- thinking
- chain-of-thought
- mlx
base_model: ByteDance/Ouro-2.6B-Thinking
---

# mlx-community/Ouro-2.6B-Thinking-4bit

This model [mlx-community/Ouro-2.6B-Thinking-4bit](https://huggingface.co/mlx-community/Ouro-2.6B-Thinking-4bit) was
converted to MLX format from [ByteDance/Ouro-2.6B-Thinking](https://huggingface.co/ByteDance/Ouro-2.6B-Thinking)
using mlx-lm version **0.28.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Ouro-2.6B-Thinking-4bit")

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)
```