Skip to main content

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.

codellama

CodeLlama-7b-hf

codellama/CodeLlama-7b-hf
text generationLicense: llama2Hashes recordedsafetensors · BIN

Content controls: not assessed.

Model from Hugging Face for text generation: codellama/CodeLlama-7b-hf · transformers

What's included

9 hosted of 17 listed

Weights
Tokenizer & config
README, LICENSE & .gitattributes

About this model

External Hugging Face catalog record for codellama/CodeLlama-7b-hf. Task: text generation. Library: transformers. Languages: code. Popularity signal at import: 316,241 downloads and 379 likes.

Quick facts

Parameters
7B
Hosted here
9 hosted of 17 listed
Full repo upstream
27 GB
Recommended file
27 GB (5 files)
Languages
code
Format
safetensors · BIN
Downloads on Hugging Face
316,241
File hashes
Hashes recorded. Date not recorded.

License & source

License: llama2

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

Upstream source →

See the JSON record →

Task
text generation
Hosted here
9 files, 13.5 GB
Full repo upstream
27 GB
Recommended file
27 GB (5 files)
Parameters
7B
Files
9 hosted of 17 listed
Added to Hugging Bay
Updated at source

FAQ

What is this model?

codellama/CodeLlama-7b-hf is an open-weights language model for text generation published by codellama, added to Hugging Bay Sep 20, 2026. Model from Hugging Face for text generation: codellama/CodeLlama-7b-hf · transformers

Can I use it commercially?

It is released under the llama2 license. Commercial use is allowed with conditions. Commercial use is permitted with obligations: Llama community license: commercial use allowed; if your products/services exceeded 700 million monthly active users (Section 2, Additional Commercial Terms) you must request a license from Meta first; the acceptable-use policy and attribution notice apply.

How big is it?

codellama/CodeLlama-7b-hf has 7B parameters. Hosted here: 9 files, 13.5 GB. Full repo upstream: 27 GB. The recommended download, a 5-file weight set, is 27 GB.

What can I download here?

Hosted here: 9 files, 13.5 GB. Full repo upstream: 27 GB. The original release is at https://huggingface.co/codellama/CodeLlama-7b-hf.

File checks and computer fit
File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 9 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-codellama-codellama-7b-hf/safety on Hugging Bay.

Will codellama/CodeLlama-7b-hf 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.

Similar hosted models

Explore hosted models