Google Gemma 4 26B A4B

Google: Gemma 4 26B A4B (free) on Openrouter

Context: 262,144 Provider: google

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...