---
license: other
license_name: nvidia-open-model-license
license_link: https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16/blob/main/LICENSE
base_model: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
library_name: mlx
pipeline_tag: image-text-to-text
tags:
  - mlx
  - nemotron
  - omni
  - multimodal
  - vision
  - audio
  - moe
language: [en]
---

# mlx-community/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-4bit

This model was converted to MLX 4-bit format from
[nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16).

`NemotronH_Nano_Omni_Reasoning_V3` — a tri-modal (text + vision + audio)
multimodal model:

- **Text backbone:** NemotronH hybrid (Mamba2 + MoE + attention), 30B total /
  ~3B active, 128-expert top-6, hidden 2688, 52 layers, 262k context.
- **Vision tower:** C-RADIOv4-H ViT (InternVL-style pixel-shuffle head → `mlp1`
  projector).
- **Audio tower:** Parakeet Conformer (learned-filterbank frontend + BatchNorm
  conv module + Transformer-XL relative-position attention → `sound_projection`).

## Conversion

Quantized with a **first-party streaming quantizer** (group_size 64, 4-bit
affine) — the stock `mlx_lm` / `mlx_vlm` `convert` tools do not yet support the
`NemotronH_Nano_Omni_Reasoning_V3` multimodal wrapper. The LLM-backbone tensor
layout is byte-identical to the text sibling
[mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-4bit](https://huggingface.co/mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-4bit);
the vision (`vision_model.*`) and audio (`sound_encoder.*`) towers are kept in
bf16. ~19 GB on disk, ~20 GB working set (Apple-silicon Mac tier).

## Use

The text backbone loads with standard MLX `nemotron_h` tooling. The vision and
audio towers require a multimodal runtime that implements the C-RADIO ViT-H and
Parakeet Conformer forward passes (e.g. the Evorix on-device engine).

## License

Derivative of `nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16` under the
**NVIDIA Open Model License**; original model © NVIDIA.