跳转到主要内容

AI models that run on this device.

Two small chat models run in a computer’s browser here; every other model is a file you download.

nvidia

Nemotron-3-Embed-8B-BF16

nvidia/Nemotron-3-Embed-8B-BF16
sentence similarity and retrievalLicense: unknownHashes recordedsafetensors

Content controls: not assessed.

Model from Hugging Face for sentence similarity: nvidia/Nemotron-3-Embed-8B-BF16 · sentence transformers

包含内容

13 hosted of 18 listed

Weights
Tokenizer & config
README, LICENSE & .gitattributes

关于此模型

External Hugging Face catalog record for nvidia/Nemotron-3-Embed-8B-BF16. Task: sentence similarity. Library: sentence transformers. Languages: multilingual, en, ar, as, bn, bg, zh, da. Popularity signal at import: 103,065 downloads and 99 likes.

基本信息

Parameters
8B
Hosted here
13 hosted of 18 listed
Full repo upstream
15.9 GB
Recommended file
15.9 GB (4 files)
Languages
multilingual, en, ar, as, bn, bg, zh, da, nl, fi, fr, de
Format
safetensors
Downloads on Hugging Face
103,065
File hashes
Hashes recorded. Date not recorded.

许可证与来源

License: unknown

No license was found in metadata, the LICENSE file or README. Check the terms before you use or share the files.

See the JSON record →

License
unknown
Task
sentence similarity and retrieval
Hosted here
13 files, 15.9 GB
Full repo upstream
15.9 GB
Recommended file
15.9 GB (4 files)
Parameters
8B
Files
13 hosted of 18 listed
Added to Hugging Bay
Updated at source
Source
nvidia/Nemotron-3-Embed-8B-BF16

FAQ

What is this model?

nvidia/Nemotron-3-Embed-8B-BF16 is an embedding model for sentence similarity and retrieval published by nvidia, added to Hugging Bay Sep 21, 2026. Model from Hugging Face for sentence similarity: nvidia/Nemotron-3-Embed-8B-BF16 · sentence transformers

Can I use it commercially?

License: unknown. Check the upstream license text or ask the model author before commercial use.

How big is it?

nvidia/Nemotron-3-Embed-8B-BF16 has 8B parameters. Hosted here: 13 files, 15.9 GB. Full repo upstream: 15.9 GB. The recommended download, a 4-file weight set, is 15.9 GB.

What can I download here?

Hosted here: 13 files, 15.9 GB. Full repo upstream: 15.9 GB.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 13 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-nvidia-nemotron-3-embed-8b-bf16/safety on Hugging Bay.

Will nvidia/Nemotron-3-Embed-8B-BF16 run on my computer?

We can’t check the fit; we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it; you can still download; fit isn’t checked.

类似的托管模型

浏览托管模型