Tool · curated 29 Aug 2026
dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8
First reported huggingface.co
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
Refusal-removed, freely downloadable LLMs like this uncensored Qwen build lower the barrier to generating harmful content and expand the pool of weaponized models defenders must account for.
A Hugging Face repository by "dealignai" publishes Qwen3.8-Flash-Next-UNCENSORED-FP8, a refusal-removed build of a Qwen model created through direct weight-level modification rather than fine-tuning or prompt tricks. The page advertises near-100% compliance on HarmBench harmful-behavior categories including chemical/biological, cybercrime/intrusion, and illegal activity while retaining most MMLU capability.