Any-to-Any
Transformers
Safetensors
PyTorch
NemotronH_Nano_Omni_Reasoning_V3
feature-extraction
nvidia
multimodal
custom_code
Eval Results
Instructions to use nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model-00006-of-00017.safetensors from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16: direct link, hf CLI and curl.
- Browser
- Download file 4 GB
-
https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16/resolve/refs%2Fpr%2F3/model-00006-of-00017.safetensors
- Command line
-
hf download hf://nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16@refs/pr/3/model-00006-of-00017.safetensors
-
curl -L -o model-00006-of-00017.safetensors https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16/resolve/refs%2Fpr%2F3/model-00006-of-00017.safetensors
4 GB
- Xet hash:
- bc4346063aaecd478ab28f5fa0f9461f895d2d3864bb8c540846f0186888ae70
- Size of remote file:
- 4 GB
- SHA256:
- 24a7ba72f08e647c2c78b0264ad4bc4f78e3d70e405e5dda50c059333ebdb3d2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.