Skip to content

Gemma 4 26B A4B (Non-reasoning)

Available

Google · 2026-04-02 · 32,000 tokens

An AI model from Google, suited to a broad range of AI workloads.

Supported modalities:textcode

Quick Overview

Text Generation2/10
Code Generation6/10
Reasoning6/10
Multimodal2/10

Benchmark Results

Scores from leading benchmark suites.

artificial analysis intelligence20.4

Performance Metrics

Latency and throughput performance.

P50 Latency
78.757tokens/sec

Dive Deeper