Any-to-Any
Transformers
Safetensors
English
NemotronH_Nano_Omni_Reasoning_V3
feature-extraction
nvidia
nemotron
multimodal
quantized
4-bit precision
int4
custom_code
compressed-tensors
Instructions to use drawais/Nemotron-3-Nano-Omni-30B-A3B-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use drawais/Nemotron-3-Nano-Omni-30B-A3B-W4A16 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("drawais/Nemotron-3-Nano-Omni-30B-A3B-W4A16", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- 1.57 kB
- 7.93 kB
- 521 Bytes
- 4.24 kB
- 6.89 kB
- 14.3 kB
- 14.4 kB
- 4.87 kB
- 14 kB
- 5.69 kB
- 2.92 kB
- 237 Bytes
- 1.93 GB xet
- 1.41 GB xet
- 1.41 GB xet
- 1.34 GB xet
- 1.41 GB xet
- 1.41 GB xet
- 1.41 GB xet
- 1.41 GB xet
- 1.41 GB xet
- 1.36 GB xet
- 1.41 GB xet
- 1.41 GB xet
- 2.12 GB xet
- 2.55 GB xet
- 2.22 MB
- 31.5 kB
- 64 kB
- 563 Bytes
- 17.1 MB xet
- 177 kB