We use an optional cookie to count visits. Your choice is remembered.

Privacy
Skip to main content
The Hugging BayFind a model

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.

BAAI

bge-m3

BAAI/bge-m3
sentence similarity and retrievalLicense: mitHashes recordedPT · ONNX · BIN

Content controls: not assessed.

Model from Hugging Face for sentence similarity: BAAI/bge-m3 · sentence transformers

View as JSON →

Model facts

bge-m3 is an embedding model for sentence similarity and retrieval. The primary file is pytorch_model.bin (2.27 GB). The primary file needs about 4 GB free for the selected file. License: MIT. The SHA-256 prefix is b5e0ce3470ab. The primary Download is available now. No tested run commands for this file yet. Some listed files are available here. The size and hash details refer to the selected file, not every file in the repository. The memory figure is estimated from recorded file size with working room included. The size line uses recorded file bytes when they are present in this model record.

What's included

Weights5 files
Tokenizer & config14 files
README, LICENSE & .gitattributes2 files

About this model

External Hugging Face catalog record for BAAI/bge-m3. Task: sentence similarity. Library: sentence transformers. Files we host have a published SHA-256.

Quick facts

Hosted here
at least 29 listed files; full count and size unknown
Full repo upstream
4.59 GB
Recommended file
2.27 GB · pytorch_model.bin
Format
PT · ONNX · BIN
Files hosted
29 of 30
Downloads on Hugging Face
31,290,962
File hashes
Hashes recorded. Date not recorded.

License & source

License: mit

Check the license text and keep the required notices when you use or share the files.

Upstream source →

See the JSON record →

Task
sentence similarity and retrieval
Hosted here
at least 29 listed files; full count and size unknown
Full repo upstream
4.59 GB
Recommended file
2.27 GB · pytorch_model.bin
Files
29 hosted of 30 listed
Added to Hugging Bay
Updated at source

FAQ

What is this model?

BAAI/bge-m3 is an embedding model for sentence similarity and retrieval published by BAAI, added to Hugging Bay Jun 29, 2026. Model from Hugging Face for sentence similarity: BAAI/bge-m3 · sentence transformers

Can I use it commercially?

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

How big is it?

Hosted here: at least 29 listed files; full count and size unknown. Full repo upstream: 4.59 GB. The recommended download, pytorch_model.bin, is 2.27 GB.

What can I download here?

Hosted here: at least 29 listed files; full count and size unknown. Full repo upstream: 4.59 GB. The original release is at https://huggingface.co/BAAI/bge-m3.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 29 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-baai-bge-m3/safety on Hugging Bay.

Will BAAI/bge-m3 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.

Other versions of this model

6 repacks listed on Hugging Face that name this model as their base (from each publisher card). This does not mean the files match the original weights.