README.md

---
base_model: nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
language:
- en
license: cc-by-nc-4.0
pipeline_tag: text-generation
library_name: transformers
tags:
- mlx
---

# sunnytu/Nemotron-Research-Reasoning-Qwen-1.5B-mlx-4Bit

The Model [sunnytu/Nemotron-Research-Reasoning-Qwen-1.5B-mlx-4Bit](https://huggingface.co/sunnytu/Nemotron-Research-Reasoning-Qwen-1.5B-mlx-4Bit) was converted to MLX format from [nvidia/Nemotron-Research-Reasoning-Qwen-1.5B](https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("sunnytu/Nemotron-Research-Reasoning-Qwen-1.5B-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)
```