---
datasets:
- PowerInfer/QWQ-LONGCOT-500K
- PowerInfer/LONGCOT-Refine-500K
base_model: PowerInfer/SmallThinker-3B-Preview
pipeline_tag: text-generation
language:
- en
library_name: transformers
tags:
- mlx
---

# mku64/SmallThinker-3B-Preview-mlx-4Bit

The Model [mku64/SmallThinker-3B-Preview-mlx-4Bit](https://huggingface.co/mku64/SmallThinker-3B-Preview-mlx-4Bit) was converted to MLX format from [PowerInfer/SmallThinker-3B-Preview](https://huggingface.co/PowerInfer/SmallThinker-3B-Preview) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mku64/SmallThinker-3B-Preview-mlx-4Bit")

prompt="hello"

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

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