---
license: other
license_name: nvidia-open-model-license
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
pipeline_tag: text-generation
datasets:
- nvidia/Nemotron-Post-Training-Dataset-v1
- nvidia/Nemotron-Post-Training-Dataset-v2
- nvidia/Nemotron-Pretraining-Dataset-sample
- nvidia/Nemotron-CC-v2
- nvidia/Nemotron-CC-Math-v1
- nvidia/Nemotron-Pretraining-SFT-v1
language:
- en
- es
- fr
- de
- it
- ja
library_name: mlx
tags:
- nvidia
- pytorch
- mlx
track_downloads: true
base_model: nvidia/NVIDIA-Nemotron-Nano-12B-v2
---

# NexVeridian/NVIDIA-Nemotron-Nano-12B-v2-3bit

This model [NexVeridian/NVIDIA-Nemotron-Nano-12B-v2-3bit](https://huggingface.co/NexVeridian/NVIDIA-Nemotron-Nano-12B-v2-3bit) was
converted to MLX format from [nvidia/NVIDIA-Nemotron-Nano-12B-v2](https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2)
using mlx-lm version **0.27.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("NexVeridian/NVIDIA-Nemotron-Nano-12B-v2-3bit")

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)
```