ai.paski.devLlama 4 Scout Instruct
llmMeta's first natively multimodal Llama, a 17B-active-parameter mixture-of-experts model (16 experts, 109B total) with a 10M-token context window.
Metadata
| org | Meta |
| released | 2025-04-05 |
| params | 109B-A17B |
| license | llama-4 |
| kind | llm |
| hf id | meta-llama/Llama-4-Scout-17B-16E-Instruct |
Benchmarks
| MMLU-Pro | 74.3 | source ↗ |
| GPQA | 57.2 | source ↗ |
Lineage
No recorded lineage — root or standalone model.
view in full graph →