# Llama 4

Meta's flagship open MoE model family with Scout (109B, 10M context) and Maverick (400B, rivaling GPT-5 on coding).

## Agent Decision Summary
- Risk level: elevated
- Source confidence: medium
- Recommended workflows: Local or private AI stack
- Permission surface: shell/files, memory
- Agent JSON: https://www.openagent.bot/models/llama-4.agent.json

## Summary
Meta's flagship open MoE model family with Scout (109B, 10M context) and Maverick (400B, rivaling GPT-5 on coding).

## What It Does
Llama 4 is a model in the models category. Meta's flagship open MoE model family with Scout (109B, 10M context) and Maverick (400B, rivaling GPT-5 on coding).

## How To Evaluate
Evaluate Llama 4 by starting from the official sources, checking its docs, demo interface surface, and running one narrow workflow before expanding scope. Recorded integrations include GitHub, Hugging Face.

## Why It Matters
Llama 4 represents Meta's latest open MoE model family, with Scout offering an unprecedented 10M token context window and Maverick rivaling GPT-5 on coding benchmarks, making it a top contender for open model evaluation.


## Best For
- Developers evaluating open MoE models with extreme long-context needs
- Teams comparing Llama 4 Maverick against GPT-5 for coding and reasoning workloads
- Builders who need a permissively licensed open model with multiple size variants

## Not For
- Teams that cannot review the Llama 4 Community License terms before deployment
- Use cases requiring verified multimodal input beyond text-based reasoning

## Fit Matrix
- Local or private AI stack: strong. Llama 4 has multiple signals for local or private ai stack, including matching tags, capabilities, category, or positioning. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Coding agent workflow: partial. Llama 4 has at least one signal for coding agent workflow, but should be checked against a real task before adoption. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Evaluation and observability: partial. Llama 4 has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Memory or RAG workflow: partial. Llama 4 has at least one signal for memory or rag workflow, but should be checked against a real task before adoption. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Browser automation: weak. Llama 4 is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Connector or protocol layer: weak. Llama 4 is not primarily positioned for connector or protocol layer in the current metadata. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.

## Evidence
- verified: Llama 4 is listed as open source. Source: License metadata: Llama 4 Community License
- verified: Llama 4 has a recorded GitHub repository: meta-llama/llama-models. Source: Resource facts and GitHub source link.
- inferred: Llama 4 supports these recorded deployment modes: local, self hosted, cloud. Source: OpenAgent decision signal metadata.
- inferred: Llama 4 is tagged with local inference, inference capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/meta-llama/llama-models

## Facts
- Category: models
- Resource type: model
- Open source: yes
- License: Llama 4 Community License
- Last verified: 2026-06-16
- GitHub repo: meta-llama/llama-models
- GitHub stars: 7500

## Capabilities
- local-inference
- inference

## Structured Use Case Tags
- local-ai
- self-hosted-ai

## Links
- GitHub: https://github.com/meta-llama/llama-models

## Structured Outputs
- JSON: https://www.openagent.bot/models/llama-4.json
- Markdown: https://www.openagent.bot/models/llama-4.md
- Agent JSON: https://www.openagent.bot/models/llama-4.agent.json
- Canonical: https://www.openagent.bot/models/llama-4