available
Weights
Scout and Maverick weights are available under Meta’s custom terms.
Inspect this claim’s source ↗Meta / FAMILY RECORD
Llama 4: license, size and what is open.
Meta’s first natively multimodal Llama generation and first Llama mixture-of-experts release.
License
Custom or artifact-specific terms: read them. Commercial use is allowed subject to the custom license, including an additional term for services above 700 million monthly active users.
Llama 4 Community License Agreement ↗Sizes and download
Scout: 109B / 17B active; Maverick: 400B / 17B active
About 217.28 GB of selected documented weights · File listing ↗
Selected artifact: meta-llama/Llama-4-Scout-17B-16E-Instruct. Format: Safetensors, BF16. File evidence checked 2026-10-11. Selected artifact license: Llama 4 Community License Agreement ↗
Scout Instruct only, 109B total and 17B active, not Maverick. Public API lists 50 shards. Gated index/config returned 401; no login/agreement acceptance or bypass. Selected weight files only; supporting files and runtime memory are separate. Not a smallest-download census or proof of hardware compatibility.
Can my computer run it?
Compatibility, runtime memory and speed are untested by Bright.
Choose your computer and inspect documented candidates →Nine things to check
Source check: . Downloads, when known, carry their own check date.
Checked release: Scout and Maverick
Sources checked 2026-09-19
- Llama 4 Scout and Maverick release
- · Primary source
The profile describes this checkpoint, not every release carrying the family name. Developer documentation is not independent reproduction.
THE MODEL / THE TERMS
Know what you are picking up.
- Parameters
- Scout: 109B / 17B active; Maverick: 400B / 17B active
- Architecture
- Early-fusion multimodal mixture-of-experts transformer.
- Modalities
- text · image
- Context
- Scout: 10M tokens; Maverick: 1M tokens
- Weights license
- Llama 4 Community License Agreement
- Commercial use
- Commercial use is allowed subject to the custom license, including an additional term for services above 700 million monthly active users.
- Memory
- Scout is described as fitting on one H100 in Int4; Maverick is described as fitting on one H100 host.
- Known quantizations
- Meta states Scout can fit on one H100 with Int4 quantization
Specifications are developer-reported. Primary release documentation ↗ · All sources and terms
NINE DIMENSIONS / NO OPENNESS SCORE
What is actually available?
Each component has its own evidence. “Not established” means this source review did not verify availability; it is not a claim that nothing exists.
available
Architecture
Meta publishes architecture and model-card details.
Inspect this claim’s source ↗available
Inference code
Official downloads and ecosystem integrations support local inference.
Inspect this claim’s source ↗not established
Training code
The complete code used to train Llama 4 was not released.
Inspect this claim’s source ↗partial
Training recipe
Meta describes key methods including multimodal pre-training and distillation.
Inspect this claim’s source ↗partial
Data information
The model card provides categories and governance information without the corpus.
Inspect this claim’s source ↗not established
Training data
No sufficiently specific public artifact was confirmed in this review.
Inspect this claim’s source ↗partial
Evaluation
Meta reports benchmark results; full evaluation reproduction is not bundled.
Inspect this claim’s source ↗restricted
Commercial use
Commercial use is governed by a custom community license with scale-based conditions.
Inspect this claim’s source ↗WHY THIS RELEASE MATTERS
What to explore.
- Native multimodality
- Very long context on Scout
- Large deployment ecosystem
WHAT THE RECORD DOES NOT ESTABLISH
Keep the limits.
- Custom license is not OSI-approved
- Training data and full training stack are not released
This record does not independently reproduce Meta’s comparative benchmark claims.
CONNECTED EVIDENCE
A release becomes a starting point.
- Explaining a novice programmer's compiler error
Researchers fine-tuned compact downloadable language models to explain C compiler errors using examples derived from real introductory-programming mistakes.
This is an author-reported research evaluation, not a school deployment or evidence of improved learning outcomes. Dataset access and the distinct Qwen and Llama model terms must be checked before reuse.
Thematic or family connections, not proof that an older application uses the selected checkpoint.
FOLLOW THE RECORD
Sources, not superlatives.
- The Llama 4 herd ↗ (institution)
Source check: 2026-09-19. AI-assisted editorial review, with no named external expert or independent hardware validation claimed. Licenses and model cards can change. Review the linked terms for the specific artifact and intended use.
Understand open source vs open weights ↗