models · meta-llama
Meta's largest open-weight model. 405B dense transformer. State-of-the-art multilingual reasoning and code generation at open-weight scale.
| Weight file SHA-256 | 10a20606e03934dd24750cfffcbf2cec5b2535086eeb5bbb7b5d0066688998c6 |
|---|---|
| Method | hf-published-sha256 |
| Publisher | meta-llama |
|---|---|
| Origin | United States |
| Licence | LLaMA-3.1 |
| Publisher’s own licence statement | llama3.1 |
| Parameters | 405,853,388,800 (405.9B) |
| Context window | 128K |
| Native precision | BF16 |
| Pulls recorded here | 760,044 |
| Downloads reported upstream | 11,308 |
| MMLU-Pro | 73.2 |
|---|---|
| GPQA Diamond | 51.5 |
| AIME 2025 | 3 |
| MATH-500 | 70.3 |
| LiveCodeBench | 30.5 |
| IFBench | 39 |
| Humanity's Last Exam | 4 |
Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.
Registry record as of 2026-10-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.