NVIDIA-Nemotron-3-Nano-4B-BF16 is a large language model released by NVIDIA, released under the other license, with a claimed knowledge cutoff of 2026-01-01. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.
Description
NVIDIA's compact Nemotron 3 generation model.
Metadata
Hugging Face stats
4,810,763 downloads on Hugging Face · 123 likes · pipeline: text-generation · library: transformers
Weight Hashes
Combined commitment: a Merkle root over the weights, config, and tokenizer hashes together (not a raw weights-only hash) -- see this project's v2 on-chain schema.
Combined SHA-2560xbdf78e29b212f115be8d61ed0226972e0865839009367412679ce49422ebc792
Combined SHA3-2560xc7e3854a498db41c37f4a3d807f91d2ef8352f896b5005eb84e86b8b149555e7
Combined BLAKE30x2917bb61b769cc7c06a45cac8222dc617eb61ce85e5a90de15046e1cccb6fc4b
Per-file breakdown
Computed locally prior to attestation; the combined hash above is the canonical on-chain commitment.
Weights file
SHA-25655d4e2519456c4a9bddf596b0748d630e3b2ce6ff6f4c2b7ed3e07e2b00dad42
SHA3-256d315ddca69edeb2b6c23fcd188bad740a41159cb62089a4a035f1e0e1e5c6374
BLAKE38412db73e9014b48815eb590951730784828ac9b71fc7e5d83b9017758ac6b4d
Config file
SHA-256fde9241f66cd414458df444a80eb535f53aef2b4b240a91f092e651fa6f27219
SHA3-25632ebbc97fc701b9908ebf56f55f97fd7e1a9909c146a7e69a1d27af6c8006f78
BLAKE3e82e7a8fcc0b2ae3136fcca936c7471706e81a6615bea9f40b2c5e82c8a4f1f9
Tokenizer file
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