Llama 4 Scout 17B-16E

Llama 4 Scout 17B-16E is a multmodal model that uses the Mixture-of-Experts (MoE) architecture and early fusion, delivering state-of-the-art results for its size class.

Try in Vertex AI View model card in Model Garden

Property Description
Model ID llama-4-scout-17b-16e-instruct-maas
Capabilities
Knowledge cutoff date August 2024
Versions
  • llama-4-scout-17b-16e-instruct-maas
    • Launch stage: GA
    • Release date: April 29, 2025
Supported regions

Model availability

United States

  • us-east5

ML processing

United States

  • Multi-region
Quota limits

us-east5:

  • QPM: 60
  • Max output: 8,192
  • Context length: 1,310,720
Pricing See Pricing.