NV-Embed-v2 safetensors download | Hugging Bay

Q: What is this model?

nvidia/NV-Embed-v2 is an embedding model for text embeddings published by nvidia, added to Hugging Bay Sep 18, 2026. Model from Hugging Face for feature extraction: nvidia/NV-Embed-v2 · transformers

Q: Can I use it commercially?

It is released under the cc-by-nc-4.0 license. Commercial use is not allowed. cc-by-nc-4.0: commercial use is not permitted; non-commercial use and adaptations require attribution.

Q: How big is it?

Hosted here: at least 12 listed files; full count and size unknown. Full repo upstream: 15.7 GB.

Q: What can I download here?

Hosted here: at least 12 listed files; full count and size unknown. Full repo upstream: 15.7 GB. The original release is at https://huggingface.co/nvidia/NV-Embed-v2.

Q: File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 12 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-nvidia-nv-embed-v2/safety on Hugging Bay.

Q: Will nvidia/NV-Embed-v2 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.

nvidia

NV-Embed-v2

Can I run NV-Embed-v2 on my computer?

It depends on your memory, processor, file format and runtime. Hugging Bay offers 12 hosted files; check the file list for the exact selection. A file-size fit is an estimate, not a successful run or speed promise. Read the license before use.

NV-Embed-v2 is an embedding model for text embeddings. Model weights are learned parameters; a runtime loads them. A hosted file is an individual file Hugging Bay can serve. SHA-256 identifies exact file bytes. The availability date above applies to this file record, not the upstream metadata update date.

As of the recorded file availability check on 2026-10-22.

Recorded SHA-256 for model-00001-of-00004.safetensors: 0ce5651268058d961eaeabd4f65a5cb5d003ac7e0e34b7095658b5d5a4802f6a. Exact file evidence · Machine-readable source facts · Run evidence and any recorded receipts. A checksum fingerprints only the named file bytes; it does not prove safety, quality, a complete multi-file selection or a successful run.

Updated 2026-10-21 · Page-copy source revision 8871bab84e1cf80aea1686a944ec335078a6c036 · Source files: apps/web/lib/model-page-template.mjs, apps/web/lib/model-page-v3.mjs, apps/web/lib/aeo-page.mjs · Full revision record

Model metadata: As of 2026-09-18 at the model source. Popularity counters are source-reported, not measured by Hugging Bay. Availability checked 2026-10-22.

nvidia/NV-Embed-v2

Model details

text embeddingsLicense: cc-by-nc-4.0SHA-256 recorded for 13 of 19 filessafetensors

Content controls: not assessed.

The catalog lists this model for finding useful details in data. Catalog sources: license, cardMetadata.license, task, cardMetadata.pipelineTag.

View as JSON →

12 hosted of 19 listed

Hashes recorded. Date not recorded.

File	आकार	SHA-256	स्रोत	डाउनलोड करें
Weights
`model-00001-of-00004.safetensors`	5 GB	`0ce56512…a4802f6a` `0ce5651268058d961eaeabd4f65a5cb5d003ac7e0e34b7095658b5d5a4802f6a`	Hosted	डाउनलोड करें
`model-00002-of-00004.safetensors`	4.92 GB	`bbd7e85b…9074d57d` `bbd7e85b57afbc74fab67e50a572590ce57dde8b5fa76fe7527c42189074d57d`	Hosted	डाउनलोड करें
`model-00003-of-00004.safetensors`	5 GB	`87c90f03…d892a85c` `87c90f033107075c9531ed8163d4b087ce77e63596c8510821da15a4d892a85c`	Hosted	डाउनलोड करें
`model-00004-of-00004.safetensors`	788.6 MB	`44ff251c…82c4c3f5` `44ff251c6b33ed89101915eb82a92575fd7d7daf9db953205f3bb4b982c4c3f5`	Hosted	डाउनलोड करें
Tokenizer & config
`1_Pooling/config.json`	298 bytes	—	Upstream only	File metadata
`config.json`	2.66 KB	`0a276d24…c4334a0f` `0a276d24c4834ae230bdee3bf771bba3fd340f54a58b7d52964bb4b0c4334a0f`	Hosted	डाउनलोड करें
`config_sentence_transformers.json`	171 bytes	`ee032a1f…92f46db2` `ee032a1f03783440fa119c46f69eb866528f8f598ed7c46dbfe3a73f92f46db2`	Hosted	डाउनलोड करें
`configuration_nvembed.py`	3.2 KB	—	Upstream only	File metadata
`instructions.json`	2.57 KB	—	Upstream only	File metadata
`model.safetensors.index.json`	28.2 KB	`f7e412ee…c03b4a26` `f7e412ee9d1fc50fe06c505fc053da24bef0172eacd5348db649349dc03b4a26`	Hosted	डाउनलोड करें
`modeling_nvembed.py`	18.6 KB	—	Upstream only	File metadata
`sentence_bert_config.json`	55 bytes	`1140b92d…25169a65` `1140b92d307aec9383d897169c9f489f3a568787b80bf760f5d7cc9d25169a65`	Hosted	डाउनलोड करें
`special_tokens_map.json`	551 bytes	`82d96d7a…857ce7db` `82d96d7a9e6ced037f12394b7ea6a5b02e6ca87e0d11edaa8d60d9be857ce7db`	Hosted	डाउनलोड करें
`tokenizer.json`	1.8 MB	`bdc45dc7…081642d9` `bdc45dc7f18a5c55e0dcb36f4f187a7c429d6aaa1693a17d20422b85081642d9`	Hosted	डाउनलोड करें
`tokenizer.model`	493.4 KB	`dadfd56d…5e134055` `dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055`	Upstream only	File metadata
`tokenizer_config.json`	997 bytes	`9eb5863e…dedbfdd2` `9eb5863ef1b6b31ec8d3ef894486324126ff015edb4cc9013e1e0402dedbfdd2`	Hosted	डाउनलोड करें
`modules.json`	349 bytes	`84e40c8e…7cf642cf` `84e40c8e006c9b1d6c122e02cba9b02458120b5fb0c87b746c41e0207cf642cf`	Hosted	डाउनलोड करें
Docs
`.gitattributes`	1.52 KB	—	Upstream only	File metadata
`README.md`	60.1 KB	—	Upstream only	File metadata

डाउनलोड की जाँच करें

In the folder where you saved config.json, run:

macOS

shasum -a 256 -- 'config.json'

Linux

sha256sum -- 'config.json'

Windows

Get-FileHash -LiteralPath 'config.json' -Algorithm SHA256

Compare the result with the recorded SHA-256.

मिलते-जुलते होस्ट किए गए मॉडल

होस्ट किए गए मॉडल देखें

NV-Embed-v2

Can I run NV-Embed-v2 on my computer?

डाउनलोड की जाँच करें

मिलते-जुलते होस्ट किए गए मॉडल

Cookies