Skip to main content
Modelllm-modelsv1.0

Llama 4 Scout

by Meta · open-source · Last verified 2026-04-24

Llama 4 Scout is Meta's efficient multimodal model in the Llama 4 family, targeting deployments where compute cost matters. It supports a long context window and demonstrates strong per-parameter efficiency. Scout is designed for use cases where teams need a capable, locally-runnable model without the resource requirements of Maverick.

https://llama.meta.com
D
DPoor
Adoption: C+Quality: B+Freshness: ACitations: FEngagement: F

Specifications

License
Open Source
Pricing
open-source
Capabilities
Integrations
Use Cases
API Available
No
Parameters
109B (17B active)
Context Window
10M tokens
Modalities
text, image, video
Training Cutoff
August 2025
Tags
llama, multimodal, efficient, open-weights, meta, long-context
Added
2026-04-24
Completeness
73%

Index Score

34
Adoption
50
Quality
70
Freshness
80
Citations
0
Engagement
0

Need help choosing the right model?

Get Expert Guidance

Explore the full AI ecosystem on Agents as a Service