Chat with Gemma 4 26B.

The mixture-of-experts Gemma: only 3.8B of its 25B runs per word, so it is much quicker than its size suggests. Reads pictures and video.

Start chatting with Gemma 4 26B now — free, no account

At a glance

  • Maker: Google
  • Active parameters: 25B
  • Context window: 256k
  • Size: Medium
  • Memory: Handles very long documents
  • Good at: Quick answers on a budget
  • Supports: tools, images, zero data retention

Announced in Gemma 4: Byte for byte, the most capable open models.

Model availability changes as upstream capacity comes and goes — the picker on the chat page shows what is ready right now.

← All models on UsingOpen