AgentHub

Google: Gemma 4 26B A4B

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total par…

Live
Open / InstallLast updated July 27, 2026

Description

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Author

google

Platform

api

Pricing model

paid

Categories

Productivity

Tags

openrouter
llm
google
image
text
video

Capabilities

  • Image input
  • 262,144 token context