---
library_name: mlx
license: other
license_name: nvidia-nemotron-open-model-license
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/
pipeline_tag: text-generation
language:
- en
tags:
- nvidia
- pytorch
- mlx
base_model: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
datasets:
- nvidia/Nemotron-CC-v2
- nvidia/Nemotron-Post-Training-Dataset-v2
- nvidia/Nemotron-Science-v1
- nvidia/Nemotron-Instruction-Following-Chat-v1
- nvidia/Nemotron-Agentic-v1
- nvidia/Nemotron-Competitive-Programming-v1
- nvidia/Nemotron-Math-Proofs-v1
- nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1
- nvidia/Nemotron-RL-instruction_following
- nvidia/Nemotron-RL-agent-calendar_scheduling
- nvidia/Nemotron-RL-instruction_following-structured_outputs
track_downloads: true
---

# NVIDIA-Nemotron-3-Nano-4B-BF16-4bit

This model [NVIDIA-Nemotron-3-Nano-4B-BF16-4bit](https://huggingface.co/NVIDIA-Nemotron-3-Nano-4B-BF16-4bit) was
converted to MLX format from [nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16)
using mlx-lm version **0.31.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("NVIDIA-Nemotron-3-Nano-4B-BF16-4bit")

prompt = "hello"

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

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