Google: Gemma 4 26B A4B (free)
google/gemma-4-26b-a4b-it:free
Context: 262,144In: $0.00/1MOut: $0.00/1MUpdated 2026-10-04
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...
Intelligence
—
Coding
39.3
Agentic
—