Hugging Face's logo

mlx-community
/
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4

Any-to-Any
MLX
Safetensors
PyTorch
NemotronH_Nano_Omni_Reasoning_V3
nvidia
multimodal
4-bit precision
Model card Files
xet
 Community
How to use from the
Use from the
MLX library
# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4 mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4

mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4

This model was converted to MLX format from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 using mlx-vlm version 0.4.5. Refer to the original model card for more details on the model.

Use with mlx 

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
2,605
Safetensors
Model size
9B params
Tensor type
U8
·
U32
·
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
Any-to-Any
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4

Base model

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Quantized
(47)
this model

Dataset used to train mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4

Collection including mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4