Gemma 4 26B A4B

About this model

Google Gemma 4 26B A4B is a 25.2B parameter Mixture-of-Experts (MoE) multimodal language model with a 256K token context window. It supports text, image, and video inputs and generates text output, featuring a configurable thinking mode for step‑by‑step reasoning. The model achieves 82.6% on MMLU Pro, 77.1% on LiveCodeBench v6, and 86.3% on MMMLU, demonstrating strong performance across reasoning and multimodal benchmarks. It is released under the Apache 2.0 license.

Technical specifications

Capabilities

Input modalities

Output modalities

Reasoning

Hybrid Default on

Knowledge horizon