Models

Gemma 4 26B A4B

Google · April 2026

A fast Gemma 4 mixture-of-experts model (3.8B active). Understands images.

  • Modalities

  • Context window

    262,144 tokens, ≈ 197,000 words · about 790 pages

  • Max output

    32,768 tokens, ≈ 25,000 words in a single answer

  • Knowledge cutoff

    January 2025

  • Size: 26B A4B

Reasoning effort

Default: Minimal

  • Minimal

  • High

Providers

Files you can attach

  • ImagesJPG, PNG, WEBP
  • DocumentsNot supported
  • Text and codeTXT, MD, CSV, TSV, RPT, LOG, PY, TS, TSX, JS, JSX, CS, GO, JAVA, KT, SWIFT, CPP, C, H, PHP, RB, SQL, SH, PS1, HTML, CSS, SCSS, JSON, YAML, YML, XML, INI

Tools

  • Web searchSupported

Features

  • StreamingSupported
  • Function callingSupported
  • Structured outputsSupported
  • Fine-tuningNot supported

Ready to try it?

Log in

Bring your own API key · Your chats stay in your browser