Cyberax AI Playbook
cyberax.com
Model · Meta · Text

Llama 4 Maverick

Meta's flagship Llama 4 model — natively multimodal, larger MoE architecture than Scout. The Llama 4 frontier-tier entry.

Modality
Text
License
Llama 4 Community License (Open weights)
Parameter size
17B active / 128E
Released
May 22, 2025
Last verified
May 10, 2026
Runs locally
Yes
Also handles
vision

Strengths

  • Larger MoE expert count than Scout — more capacity per token
  • Native multimodal across text and vision
  • Strong instruction following at frontier scale

Weaknesses

  • Heavier deployment footprint than Scout
  • Community License restricts use at >700M MAU

Try it

WhereTypeNotes
Hugging Face weights Gated — accept Community License
OpenRouter hosted-api API key required

Version history

  1. Llama 4 Maverick May 2025 Current
  2. Llama 4 Scout May 2025

Change log

  • — Initial entry. Sighted on Hugging Face (lastModified 2025-05-22).