Qwen3.5 35B A3B uncensored heretic Native MTP Preserved is Out Now With the Full 785 MTPs Preserved and Retained, Available in Safetensors, GGUFs. NVFP4, NVFP4 GGUFs and GPTQ-Int4 Formats
The user LLMFan46 has released two uncensored versions of the Qwen3.5 model: a 27B parameter model and a 35B parameter model named A3B. These models are available in various formats including Safetensors, GGUFs, NVFP4, and GPTQ-Int4. The user clarifies that while Qwen3.5 and Qwen3.6 share the same architecture, Qwen3.5 is optimized for general-purpose AI assistance, whereas Qwen3.6 is geared towards agentic and coding tasks. AI
IMPACT New uncensored models offer users more flexibility for general AI tasks.