AI Potluck
Contribute
Back to Gap Map Model components / Embeddings & retrieval models

Nemotron Embed

NVIDIA
open weights / Overall score: 4.0(strong)

Nemotron Embed is NVIDIA's text embedding line for retrieval-augmented generation, now in its third generation. The current Nemotron-3-Embed release ships 1B and 8B bidirectional encoders with average pooling and 2048-dimension output, in BF16 and NVFP4 builds; the preceding generation - llama-embed-nemotron-8b and llama-nemotron-embed-1b-v2 - is still distributed. The line is tuned for multilingual and cross-lingual retrieval and evaluated on RTEB, MMTEB retrieval and the text split of ViDoRe-V3.

Every Nemotron Embed checkpoint reads `license: other` on the Hub, so each generation's license was confirmed by reading its own license body rather than trusted from a tag.

Openness

3 medium confidence
3.0
weights
open(ungated BF16 and NVFP4 checkpoints at 1B and 8B)
data
components-listed(161 dataset files over 8.5M+ points, public sources enumerated with links, synthetic generation described
code
partial(inference and pooling examples on the card
license
OpenMDW-1.1(Linux Foundation OpenMDW License Agreement v1.1, governing the current Nemotron-3-Embed release)

The current Nemotron-3-Embed release is licensed under OpenMDW-1.1, which permits use of the model materials without restriction beyond retaining the agreement and origin notices in any redistribution. The earlier generation ships under different terms: llama-embed-nemotron-8b carries an NVIDIA license restricted to non-commercial research, more restrictive than the current release.

  • https://huggingface.co/api/models/nvidia/Nemotron-3-Embed-1B-BF16 recorded 2026-09-11

    gated: false; private: false; cardData license other, license_name openmdw-1.1, license_link openmdw.ai.

  • https://huggingface.co/nvidia/llama-embed-nemotron-8b/raw/main/LICENSE recorded 2026-09-11

    The NVIDIA License governing the previous-generation 8B checkpoint: section 3.3 states the Work and any derivative works may only be used or intended for use non-commercially, meaning non-commercial research purposes only, with NVIDIA itself excepted.

  • https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16/raw/main/README.md recorded 2026-09-11

    license: other with license_name openmdw-1.1 and a link to openmdw.ai; the dataset section gives 8.5M+ data points across 161 dataset files, enumerates the public datasets with links, and describes the synthetic generation, without offering the mixture for download; usage is inference and pooling code only.

  • https://openmdw.ai/license/1-1/ recorded 2026-09-11

    OpenMDW-1.1 grants permission to deal in the Model Materials without restriction under copyright, patent, database and trade secret rights, requires only that a redistribution retain the agreement and notices of origin, terminates on a patent or copyright suit, and imposes no restriction on the use, modification or sharing of outputs.

Adoption

4 high confidence
4.0

Adoption is measured as Hugging Face downloads summed across the five text-embedding checkpoints spanning both the current and the previous Nemotron generation, most of them for the newest 1B model. The earlier generation counts toward adoption even though a different license governs it, and the separate visual-document and Cosmos embedding lines are excluded.

Capability

4 high confidence
4.0

Nemotron Embed's current 1B checkpoint scores 72.38 on RTEB and 71.04 on MMTEB retrieval, and the generation it replaces previously topped the full MMTEB v2 leaderboard by Borda rank. It falls short of Harrier-OSS's 74.3 MMTEB v2 mean, though the two are not measured on the same table: NVIDIA reports the retrieval split and RTEB.

Verified 2026-09-11