models · meta-llama
Smallest Llama 3.2 model. On-device, edge-optimized, multilingual.
| Weight file SHA-256 | fc19e633aae49536a20f227c1577dd27b77cc39dde1496bd2c498a76d13766e3 |
|---|---|
| Method | self-download-failed |
| Publisher | meta-llama |
|---|---|
| Origin | United States |
| Licence | Llama-3.2-Community |
| Publisher’s own licence statement | llama3.2 |
| Parameters | 1,235,814,400 (1.24B) |
| Context window | 60,000 tokens |
| Modality | text->text |
| Native precision | BF16 |
| Pulls recorded here | 54,035 |
| Downloads reported upstream | 6,303,233 |
| MMLU-Pro | 20 |
|---|---|
| GPQA Diamond | 19.6 |
| MATH-500 | 14 |
| LiveCodeBench | 1.9 |
| IFBench | 22.8 |
| Humanity's Last Exam | 5.5 |
Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.
| Hardware | Engine | Build measured | Decode, 1 stream | Label | Reported by |
|---|---|---|---|---|---|
| GeForce RTX 5080 | llama.cpp | Q8_0 | 448 tok/s @ 4,096 | candidate | localmaxxing |
| Intel Arc Pro B60 | llama.cpp | Q8_0 | 195 tok/s @ 4,096 | candidate | localmaxxing |
From local-ai-registry (MIT), commit 124959d: 2 runs across 2 machines, 0 validated — model revision and runtime pinned, launch accepted — and 2 candidate, their label for useful evidence without a reproducible-launch promise.
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.