Name: NVIDIA-Nemotron-3-Nano-4B-BF16
Creator: NVIDIA
License: NVIDIA Open Model License (verify)

NVIDIA-Nemotron-3-Nano-4B-BF16 is a large language model released by NVIDIA, released under the NVIDIA Open Model License (verify) license, with a claimed knowledge cutoff of 2026-01-01. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

NVIDIA's compact Nemotron 3 generation model.

Metadata

Type: LLM
Issuer: NVIDIA
License: NVIDIA Open Model License (verify)
Size: 7.40 GB
Knowledge cutoff: 2026-01-01
Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
Revision: dfaf35de3e30f1867dd8dbc38a7fc9fb52d3914f

Hugging Face stats

4,810,763 downloads on Hugging Face · 123 likes · pipeline: text-generation · library: transformers

Weight Hashes

Weights file

model.safetensors · 7.40 GB

SHA-25655d4e2519456c4a9bddf596b0748d630e3b2ce6ff6f4c2b7ed3e07e2b00dad42

SHA3-256d315ddca69edeb2b6c23fcd188bad740a41159cb62089a4a035f1e0e1e5c6374

BLAKE38412db73e9014b48815eb590951730784828ac9b71fc7e5d83b9017758ac6b4d

Config file

config.json · 1.40 KB

SHA-256fde9241f66cd414458df444a80eb535f53aef2b4b240a91f092e651fa6f27219

SHA3-25632ebbc97fc701b9908ebf56f55f97fd7e1a9909c146a7e69a1d27af6c8006f78

BLAKE3e82e7a8fcc0b2ae3136fcca936c7471706e81a6615bea9f40b2c5e82c8a4f1f9

Tokenizer file

tokenizer.json · 16.29 MB

SHA-256623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7

SHA3-2562c553f216cf81b5413fef2a64fc0558163bfc108c067254f60282cedf2f75587

BLAKE329a5eae59f68dc4d0dc2a7d67c95e24291a7ee8b88ac0afaaf2d2200abf69a23

Verify it yourself

curl -L -o "model.safetensors" "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16/resolve/dfaf35de3e30f1867dd8dbc38a7fc9fb52d3914f/model.safetensors"
sha256sum "model.safetensors"

Expected SHA-256: 55d4e2519456c4a9bddf596b0748d630e3b2ce6ff6f4c2b7ed3e07e2b00dad42

View source →

WEIGHT REGISTRY

NVIDIA-Nemotron-3-Nano-4B-BF16 (2026)