Google: Gemma 4 26B A4B generative

Описание

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...

Возможности

Модальности

Характеристики

API и примеры кода

from openai import OpenAI

client = OpenAI(
    base_url="https://infergate.ru/api/v1",
    api_key="ig-•••",
)

resp = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-it",
    messages=[{"role": "user", "content": "Привет!"}],
)
print(resp.choices[0].message.content)

Поддерживаемые параметры запроса