A GGUF (llama.cpp) build of Qwen/Qwen3Guard-Gen-0.6B, quantized to Q8_0, used as the content-safety guard for Beyond Logic Labs' game Netshell. It runs in-process as an engine-managed llama-server child and classifies free text into the model's native safety categories.

Classification runs in response mode (a user turn plus the assistant turn under judgement); the model emits a short Safety: <verdict>\nCategories: ... block.

Apache-2.0, inherited from the base model. All credit for the model itself goes to the Qwen team; this repository only redistributes a quantized build. See the base model card for details.