models · meta-llama

Llama 4 Maverick

Meta Llama 4 Maverick — mid-size multimodal MoE (17B active / 400B total). Natively multimodal; trained on a mixture of text and image data.

Compare Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Weight file SHA-256	f750bebe00a0e7f684050eafc72867a72dfbab3588186bcf08d17f88398bcd81
Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	meta-llama
Origin	United States
Licence	LLaMA-4
Publisher’s own licence statement	other
Parameters	401,583,781,376 (401.6B)
Context window	256K
Modality	text+image->text
Native precision	BF16
Pulls recorded here	610,015
Downloads reported upstream	9,081

Reported scores

MMLU-Pro	80.9
GPQA Diamond	67.1
AIME 2025	19.3
MATH-500	88.9
LiveCodeBench	39.7
IFBench	43
Humanity's Last Exam	4.9

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Elsewhere in the registry

All models → Browse with filters → What will run on my hardware? →

Registry record as of 2026-06-13. 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.