TPSTokens Per Second

Gemma 4

Google DeepMind🇺🇸 United States
active
Compare with other models →
Context window256K tokens

Version History

4.0major

Gemma 4 introduces multimodal support, 256K context window, Apache 2.0 permissive licensing, and mixture of experts variant. First major version update with explicit focus on enterprise deployment without data usage restrictions.

1.0major

Gemma 4 introduces multimodal support across text, image, video, and audio (small models), with context windows up to 256K, native reasoning modes, and function calling. Four model sizes (E2B 2.3B to 31B dense) target deployment from mobile to enterprise, with significant reasoning and coding benchmark improvements over Gemma 3.

Coverage

model releaseGoogle DeepMind

Google DeepMind releases Gemma 4 with four model sizes, up to 256K context, multimodal support

Google DeepMind released Gemma 4, an open-weights multimodal model family in four sizes (2.3B to 31B parameters) with context windows up to 256K tokens. All models support text and image input, with audio native to E2B and E4B variants. The Gemma 4 31B dense model scores 85.2% on MMLU Pro, 89.2% on AIME 2026, and 80.0% on LiveCodeBench—significant improvements over Gemma 3.

2 min read
google-deepmindgemma-4multimodal