Llama 3.1 405B Instruct
Metaยทmeta/llama-3.1-405b-instruct
The largest openly available foundation model in existence, trained on over 15 trillion tokens with 128k context support.
Open WeightsOpenTool CallingStructured OutputsNatural Language ProcessingArtificial Intelligence
Context
128,000
Output Limit
8,192
Linked Papers
52
Citations
2.4K
Release Date
Jul 23, 2024
Model Specifications
- Lab / Vendor
- Meta
- Model Family
- Meta
- Modality
- text
- Architecture
- Dense 16k-GPU Scale GQA Transformer
- Parameters
- 405B Dense
- Context Window
- 128,000
- Max Output
- 8,192
- Input / Output Price
- $1.25 / $3.5 per 1M
- License
- Llama 3.1 Community
Research & Evaluation Papers
Academic evaluations, empirical benchmarks, and publications for Llama 3.1 405B Instruct.
Sort