PluelyPluelyDocs

Models · Google

Pluely × Google: Gemma 4 26B A4B (free)

Text → TextNo setup · no API key

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

How Google: Gemma 4 26B A4B (free) works in Pluely

Related models