Skip to content

Google · 2B · transformer-decoder

2025-09-10 33K context 2B params

Use Cases

chat reasoning multilingual vision

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec43.3 GBGood
Q8_084.2 GBGood
F16166.5 GBExcellent

About this model

Gemma 3n E2B is Google's ultra-compact 2B-parameter multimodal model from the Gemma 3n family, optimized for edge and on-device inference. It handles both text and vision inputs while requiring minimal memory and compute resources. As the smallest model in the Gemma 3n lineup, the E2B variant is ideal for resource-constrained environments where a lightweight model with multimodal capabilities is needed, such as mobile devices and IoT applications.