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...
Details
| Field | Value |
|---|---|
| id | models/gemma-4-26b-a4b-it |
| context_length | 262144 |
| max_output_tokens | 32768 |
| quantization | unknown |