Ops-Colqwen3-4B safetensors download | Hugging Bay

Q: What is this model?

OpenSearch-AI/Ops-Colqwen3-4B is an open-weights language model for visual document retrieval published by OpenSearch-AI, added to Hugging Bay Jun 29, 2026. Model from Hugging Face for visual document retrieval: OpenSearch-AI/Ops-Colqwen3-4B · transformers

Q: Can I use it commercially?

It is released under the apache-2.0 license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

Q: How big is it?

OpenSearch-AI/Ops-Colqwen3-4B has 4B parameters. Hosted here: at least 14 listed files; full count and size unknown. Full repo upstream: 8.9 GB.

Q: What can I download here?

Hosted here: at least 14 listed files; full count and size unknown. Full repo upstream: 8.9 GB. The original release is at https://huggingface.co/OpenSearch-AI/Ops-Colqwen3-4B.

Q: File pattern scans

Automated file-pattern scans flagged nothing — not a safety guarantee. 14 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-opensearch-ai-ops-colqwen3-4b/safety on Hugging Bay.

Q: Will OpenSearch-AI/Ops-Colqwen3-4B 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.

OpenSearch-AI

Ops-Colqwen3-4B

OpenSearch-AI/Ops-Colqwen3-4B

visual document retrievalLicense: apache-2.0Hashes recordedGITATTRIBUTES · MD · PY · JSON · JINJA · TXT · SAFETENSORS

Content controls: not assessed.

Model from Hugging Face for visual document retrieval: OpenSearch-AI/Ops-Colqwen3-4B · transformers

View as JSON →

Hashes recorded; date unavailable

File	Size	SHA-256	Source	Download
Weights
`model-00001-of-00002.safetensors`	4.99 GB	`2905b909…d1675f16` `2905b909c01c687780409eadd4a3011543c47ef87df5f6257c1e70dfd1675f16`	Download availability is unknown.	File metadata
`model-00002-of-00002.safetensors`	3.9 GB	`901e7423…ebb20824` `901e74232526c101dc88ce9d48cc77230507f47ed49d7ff0c76fe4fbebb20824`	Download availability is unknown.	File metadata
Tokenizer & config
`__init__.py`	322 bytes	—	Download availability is unknown.	File metadata
`chat_template.jinja`	5.29 KB	`3636d0f0…91a489e4` `3636d0f0bd6bef02654cdffdc447b79cb2cef8ab02cc75267345946291a489e4`	Download availability is unknown.	File metadata
`config.json`	1.84 KB	`038d3115…bcf21b8b` `038d311590c71416b6834897cbdb6f7d86e18ce93d48725ee97c6c33bcf21b8b`	Download availability is unknown.	File metadata
`configuration_ops_colqwen3.py`	435 bytes	—	Download availability is unknown.	File metadata
`merges.txt`	1.67 MB	`8831e4f1…08a904d5` `8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5`	Download availability is unknown.	File metadata
`model.safetensors.index.json`	60.6 KB	`62ccf663…e231fde4` `62ccf663cce2482ee0d3cf01f6b62e1f76d2a678f5008ac4251a0af4e231fde4`	Download availability is unknown.	File metadata
`modeling_ops_colqwen3.py`	3.83 KB	—	Download availability is unknown.	File metadata
`preprocessor_config.json`	831 bytes	`e119dd9d…7f391af6` `e119dd9df9b914988b6b1e957b7101bb28520362291447a84bffc5387f391af6`	Download availability is unknown.	File metadata
`processing_ops_colqwen3.py`	5.6 KB	—	Download availability is unknown.	File metadata
`scripts/ops_colqwen3_embedder.py`	4.98 KB	—	Download availability is unknown.	File metadata
`tokenizer_config.json`	5.48 KB	`b7746862…b506058c` `b77468628b7845f81d6705b8c68fe3ea2aca320204b0dcc5a1f2a9c0b506058c`	Download availability is unknown.	File metadata
`video_preprocessor_config.json`	819 bytes	`877111c3…46b26d4a` `877111c3cf35151a15a991643d89cfa96a7fc20e9efe12bd47f1fea746b26d4a`	Download availability is unknown.	File metadata
`vocab.json`	2.78 MB	`ca10d7e9…b1440910` `ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910`	Download availability is unknown.	File metadata
`added_tokens.json`	707 bytes	`c0284b58…0833c680` `c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680`	Download availability is unknown.	File metadata
`special_tokens_map.json`	613 bytes	`76862e76…dd3a1ecd` `76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd`	Download availability is unknown.	File metadata
`tokenizer.json`	11.4 MB	`aeb13307…4492dae4` `aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4`	Download availability is unknown.	File metadata
Docs
`.gitattributes`	1.57 KB	—	Download availability is unknown.	File metadata
`README.md`	5.6 KB	`91524e59…90335c76` `91524e59333d152eb01f25ed3899acde81270e3a829c8448acdfd59690335c76`	Download availability is unknown.	File metadata

Check a download

In the folder where you saved README.md, run:

macOS

shasum -a 256 -- 'README.md'

Linux

sha256sum -- 'README.md'

Windows

Get-FileHash -LiteralPath 'README.md' -Algorithm SHA256

Compare the result with the recorded SHA-256.

Similar hosted models

Explore hosted models

Cookies

Ops-Colqwen3-4B

Check a download

Similar hosted models