---
license: apache-2.0
base_model:
- nex-agi/Nex-N2-mini
library_name: mlx-vlm
pipeline_tag: image-text-to-text
tags:
- mlx
- mlx-vlm
- apple-silicon
- vision-language
- image-text-to-text
- qwen3.5
- nex-n2
- 4-bit
---

# Nex-N2-mini-MLX-VLM-4bit

Native MLX-VLM 4-bit quantized version of [`nex-agi/Nex-N2-mini`](https://huggingface.co/nex-agi/Nex-N2-mini).

## Summary

- **Base model:** `nex-agi/Nex-N2-mini`
- **Format:** native MLX / MLX-VLM
- **Quantization:** 4-bit MLX-VLM quantization
- **Vision:** supported
- **MTP:** not included
- **Target runtime:** MLX-VLM / oMLX / Apple Silicon

This version is intended as the general stable release. It is compatible with direct `mlx-vlm.generate` loading.

## Quick test

~~~bash
python3 -m mlx_vlm.generate \
  --model joowon-jang/Nex-N2-mini-MLX-VLM-4bit \
  --image /path/to/image.jpg \
  --prompt "Describe this image in one sentence." \
  --max-tokens 128 \
  --temp 0.0
~~~

## Notes

For oMLX Native MTP speculative decoding, use:

`joowon-jang/Nex-N2-mini-MLX-VLM-4bit-MTP`

## License

Apache-2.0, following the base model license.