models · meta-llama
The default workhorse small model: cheap to host, broad ecosystem support, strong 8B-class quality.
| Weight file SHA-256 | deede0538205756c838ef6e33997ff1433ebc3b7d5587193d0d54de695c6ade5 |
|---|---|
| Method | hf-published-sha256 |
| Publisher | meta-llama |
|---|---|
| Origin | United States |
| Licence | Llama-3.1 |
| Publisher’s own licence statement | llama3.1 |
| Parameters | 8,030,261,248 (8.03B) |
| Context window | 128K |
| Modality | text->text |
| Native precision | BF16 |
| Pulls recorded here | 2,600,061 |
| Downloads reported upstream | 5,620,539 |
| MMLU-Pro | 47.6 |
|---|---|
| GPQA Diamond | 25.9 |
| AIME 2025 | 4.3 |
| MATH-500 | 51.9 |
| LiveCodeBench | 11.6 |
| IFBench | 28.6 |
| Humanity's Last Exam | 5.3 |
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.