Model dossier

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 parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

ProviderGoogle Start comparison

Context262,144

Max outputn/a

Pricing viewTVP price

Identity

Google: Gemma 4 26B A4B

Model ID: google/gemma-4-26b-a4b-it
Canonical slug: google/gemma-4-26b-a4b-it-20260403
Knowledge cutoff: n/a
Created: 4/3/2026

Capabilities

imagetextvideotoolsstructured

Modalities

text+image+video->textimagetextvideo

Capacity

Context262,144

Max outputn/a

TokenizerGemma