Meta-Llama-3.1-8B-Instruct-FP8
RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8Content controls: not assessed.
Model from Hugging Face for text generation: RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 · transformers
Contenu inclus
8 hosted of 11 listed
À propos de ce modèle
External Hugging Face catalog record for RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8. Task: text generation. Library: transformers. Languages: en, de, fr, it, pt, hi, es, th. Base model: meta-llama/Meta-Llama-3.1-8B-Instruct. Popularity signal at import: 129,662 downloads and 45 likes.
Informations clés
- Parameters
- 8B
- Hosted here
- 8 hosted of 11 listed
- Full repo upstream
- 9.09 GB
- Recommended file
- 9.08 GB (2 files)
- Languages
- en, de, fr, it, pt, hi, es, th
- Format
- safetensors
- Downloads on Hugging Face
- 129,662
- File hashes
- Hashes recorded. Date not recorded.
Licence et source
License: llama3.1
Check the license text and keep the required notices when you use or share the files.
Upstream source →- License
- Llama 3.1 Community. Custom terms, read before use
- Task
- text generation
- Hosted here
- 8 files, 9.09 GB
- Full repo upstream
- 9.09 GB
- Recommended file
- 9.08 GB (2 files)
- Parameters
- 8B
- Files
- 8 hosted of 11 listed
- Download
- Download here (8 hosted files)
- Added to Hugging Bay
- Updated at source
FAQ
What is this model?
RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 is an open-weights language model for text generation published by RedHatAI, added to Hugging Bay Sep 21, 2026. Model from Hugging Face for text generation: RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 · transformers
Can I use it commercially?
It is released under the llama3.1 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?
RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 has 8B parameters. Hosted here: 8 files, 9.09 GB. Full repo upstream: 9.09 GB. The recommended download, a 2-file weight set, is 9.08 GB.
What can I download here?
Hosted here: 8 files, 9.09 GB. Full repo upstream: 9.09 GB. The original release is at https://huggingface.co/RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8.
File checks and computer fit
File pattern scans
Automated file-pattern scans flagged nothing; not a safety guarantee. 8 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-redhatai-meta-llama-3-1-8b-instruct-fp8/safety on Hugging Bay.
Will RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 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.
Repack of meta-llama/meta-llama-3.1-8b-instruct (from the publisher card on Hugging Face). This does not mean the files match the original weights.
11 other repacks declare the same base on their cards.