Qwen3Guard-Gen-0.6B is a specialized model designed to evaluate whether user queries are safe according to a detailed safety policy. It classifies content into categories such as violent, sexual, PII, or jailbreak attempts. The model uses a structured prompt template and is intended for integration into LLM pipelines as a guardrail.
In the Foundation models & chat space, Qwen3Guard Gen 0.6B takes a focused approach. Automatically detecting and categorizing unsafe, controversial, or prohibited content in user queries before generation. Qwen3Guard Gen 0.6B is an open-source project aimed at developers. The project is open source (Open Source). Qwen3Guard Gen 0.6B is available on the web, the command line, and API.
Behind Qwen3Guard Gen 0.6B is Qwen, and it first shipped in 2026. The project is developed in the open on GitHub with 486 stars. Among its 3 catalogued features are Safety Evaluation, Content Classification, and Jinja Chat Template.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do