Use the NGC CLI to download:
Copied!
Model
Nemotron-Nano-3-30B-A3B is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks.
Use the NGC CLI to download:
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
chat_template.jinja | 10.59 KB | December 11, 2025 UTC | |
checksums.blake3 | 2.03 KB | December 11, 2025 UTC | |
config.json | 1.82 KB | December 11, 2025 UTC | |
configuration_nemotron_h.py | 12.59 KB | December 11, 2025 UTC | |
generation_config.json | 197 B | December 11, 2025 UTC | |
model-00001-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00002-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00003-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00004-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00005-of-00013.safetensors | 4.64 GB | December 11, 2025 UTC | |
model-00006-of-00013.safetensors | 4.66 GB | December 11, 2025 UTC | |
model-00007-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00008-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00009-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00010-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00011-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00012-of-00013.safetensors | 4.65 GB | December 11, 2025 UTC | |
model-00013-of-00013.safetensors | 3.02 GB | December 11, 2025 UTC | |
model.safetensors.index.json | 598.92 KB | December 11, 2025 UTC | |
modeling_nemotron_h.py | 81.24 KB | December 11, 2025 UTC | |
special_tokens_map.json | 420 B | December 11, 2025 UTC | |
tokenizer_config.json | 183.98 KB | December 11, 2025 UTC | |
tokenizer.json | 16.29 MB | December 11, 2025 UTC |