Sobre

Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based on the MatFormer architecture, it supports nested submodels and modular composition via the Mix-and-Match framework. Gemma 3n models are optimized for low-resource deployment, offering 32K context length and strong multilingual and reasoning performance across common benchmarks. This variant is trained on a diverse corpus including code, math, web, and multimodal data.

Família do Modelo

Gemma 3 270M2025-08-14 Gemma 3n E4B Instruct2025-06-26 Gemma 3n E2B Instruct2025-06-26 gemma 3n E2B it2025-06-12 Gemma 3n E4B Instruct Preview (May '25)2025-05-20 Google: Gemma 3n 4B2025-05-20 Google: Gemma 3n 4B (free)2025-05-20 Gemma 3 1B Instruct2025-03-13

Google: Gemma 3n 2B (free)

Sobre

Família do Modelo

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Open Source

Comparação Rápida

Modelos Similares