Verified record · from the answer index
ditto--ai/qwen3guard-gen-4b
modeltested · static-verifiedscore 60/100signed passport ✓published 206d ago · verified 2026-10-241,700,000 uses
A 4B-parameter safety and content moderation model that classifies user prompts and assistant responses as Safe, Unsafe, or Controversial with fine-grained category labels and refusal detection. Supports 119 languages.
Declared tools (1)
ditto--ai/qwen3guard-gen-4b
model:replicate:ditto--ai/qwen3guard-gen-4b