README.md

---
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
- fr
- es
- it
- de
- ja
- zh
tags:
- nvidia
- pytorch
- nemotron-3
- latent-moe
- mtp
- mlx
datasets:
- nvidia/nemotron-post-training-v3
- nvidia/nemotron-pre-training-datasets
track_downloads: true
base_model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
---

# will3509111/Nemotron-3-Super-120B-A12B-MLX-MXFP4

This model [will3509111/Nemotron-3-Super-120B-A12B-MLX-MXFP4](https://huggingface.co/will3509111/Nemotron-3-Super-120B-A12B-MLX-MXFP4) was
converted to MLX format from [nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16)
using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("will3509111/Nemotron-3-Super-120B-A12B-MLX-MXFP4")

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)
```