AlibabaQwen Guard
Qwen3Guard-Gen-8B
Qwen3Guard-Gen treats moderation as a generative instruction task. It is trained from Qwen3 and supports 119 languages and dialects.
Practical use
Practical guidance. Use disagreements with smaller classifiers as review cases rather than assuming the larger model is always correct. Keep the original text and reason category available to a human reviewer.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Qwen/Qwen3Guard-Gen-8B |
| Training family | The Guard series uses 1.19 million labelled prompts and responses.Qwen3Guard-Gen-8B model card |
| Interface | Generative safety classification.Qwen3Guard-Gen-8B model card |
| Licence | Apache 2.0.Qwen3Guard-Gen-8B model card |
Related models
- Qwen3Guard-Gen-0.6B
Alibaba · Qwen Guard
A 600-million-parameter Qwen3 moderation model for complete text in 119 languages and dialects.
Launch date not confirmedDownloadable - Qwen3Guard-Gen-4B
Alibaba · Qwen Guard
Four-billion-parameter generative moderation model trained from Qwen3 for 119 languages and dialects.
Launch date not confirmedDownloadable - Qwen3Guard-Stream-0.6B
Alibaba · Qwen Guard
A 600-million-parameter streaming moderation model with token-level classification.
Launch date not confirmedDownloadable