Qwen3Guard-Gen-0.6B

Description

Qwen3Guard-Gen-0.6B is Alibaba Qwen's lightweight safety-moderation model built on Qwen3. It frames safety classification as instruction following: given a user prompt, or a prompt plus an assistant response, it outputs a Safe, Controversial or Unsafe rating, the harm categories involved (violence, illegal acts, sexual content, PII, self-harm, unethical acts, politically sensitive topics, copyright, jailbreak) and, for responses, whether the answer was a refusal. Supports 119 languages and dialects.

Providers

OVHcloud

View provider details and policies.

Quantization: FP16

Capabilities

EU-Compliant API Access

Use Qwen3Guard-Gen-0.6B with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/qwen3guard-gen-0.6b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'