Gemma 4 26B A4B

Description

Gemma 4 26B A4B is Google DeepMind's open-weight Mixture-of-Experts model (25.2B total, 3.8B active parameters; 128 experts with 8 active plus 1 shared) for fast reasoning, coding, agentic and multimodal work. It takes text and image input, produces text, supports a 256K-token context, configurable thinking, native function calling and the system role, and was pre-trained on 140+ languages.

Providers

Scaleway

View provider details and policies.

Quantization: BF16

Capabilities

EU-Compliant API Access

Use Gemma 4 26B A4B with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.pro/api/v1/chat/completions \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'