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...
Rank
#125
Up 12% week over week
Tokens
16.3B
2026-08-14
Requests
3.5M
3,531,813
Tool calls
-
Input / M
Free
Output / M
Free
Cache / M
Free
Context
262K
262,144 tokens