Ir para o conteúdo principal

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.

facebook

metaclip-2-worldwide-m16

facebook/metaclip-2-worldwide-m16
zero shot image classificationLicense: cc-by-nc-4.0Hashes recordedsafetensors

Content controls: not assessed.

Model from Hugging Face for zero shot image classification: facebook/metaclip-2-worldwide-m16 · transformers

Informações do modelo

metaclip-2-worldwide-m16 is a vision model for zero shot image classification. The primary file is model.safetensors (2.15 GB). The primary file needs about 4 GB free for the selected file. License: CC BY-NC 4.0. The SHA-256 prefix is b95f722d4874. The primary Download is available now. No tested run commands for this file yet. See Files for current download availability. 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.

O que está incluído

6 hosted of 9 listed

Weights
Tokenizer & config
README, LICENSE & .gitattributes

Sobre este modelo

External Hugging Face catalog record for facebook/metaclip-2-worldwide-m16. Task: zero shot image classification. Library: transformers. Popularity signal at import: 28 downloads and 4 likes.

Informações básicas

Hosted here
6 hosted of 9 listed
Full repo upstream
2.23 GB
Recommended file
2.15 GB · model.safetensors
Format
safetensors
Downloads on Hugging Face
28
File hashes
Hashes recorded. Date not recorded.

Licença e origem

License: cc-by-nc-4.0

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

Upstream source →

See the JSON record →

Task
zero shot image classification
Hosted here
6 files, 2.21 GB
Full repo upstream
2.23 GB
Recommended file
2.15 GB · model.safetensors
Files
6 hosted of 9 listed
Added to Hugging Bay
Updated at source

FAQ

What is this model?

facebook/metaclip-2-worldwide-m16 is a vision model for zero shot image classification published by facebook, added to Hugging Bay Sep 20, 2026. Model from Hugging Face for zero shot image classification: facebook/metaclip-2-worldwide-m16 · transformers

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.

How big is it?

Hosted here: 6 files, 2.21 GB. Full repo upstream: 2.23 GB. The recommended download, model.safetensors, is 2.15 GB.

What can I download here?

Hosted here: 6 files, 2.21 GB. Full repo upstream: 2.23 GB. The original release is at https://huggingface.co/facebook/metaclip-2-worldwide-m16.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 6 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-facebook-metaclip-2-worldwide-m16/safety on Hugging Bay.

Will facebook/metaclip-2-worldwide-m16 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.