models · meta-llama
Meta Llama 3.1 70B — strong multilingual instruct model, reference open-weight at 70B.
| Weight file SHA-256 | e7167816421d189e6507c7be5ae79eac8de6aaf673b3469c1aeed509f088ec09 |
|---|---|
| Method | hf-published-sha256 |
| Publisher | meta-llama |
|---|---|
| Origin | United States |
| Licence | Meta-Llama-3.1 |
| Publisher’s own licence statement | llama3.1 |
| Parameters | 70,553,706,496 (70.6B) |
| Context window | 131,072 tokens |
| Modality | text->text |
| Native precision | BF16 |
| Pulls recorded here | 98,036 |
| Downloads reported upstream | 203,439 |
| MMLU-Pro | 67.6 |
|---|---|
| GPQA Diamond | 58.4 |
| AIME 2025 | 4 |
| MATH-500 | 64.9 |
| LiveCodeBench | 23.2 |
| IFBench | 34.4 |
| Humanity's Last Exam | 4.5 |
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.