license: apache-2.0 tags:

• uncensored
• qwen3.5
• moe
• safetensors
• nvfp4
• compressed-tensors
• llm-compressor
• vision
• multimodal language:
• en
• zh
• multilingual pipeline_tag: image-text-to-text base_model: Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors quantized_by: Li101

Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4

NVFP4 quantized version of Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors, which is the "Aggressive" uncensoring variant of Qwen/Qwen3.5-35B-A3B. Includes full vision encoder weights (BF16, unquantized).

Quantization Details

Calibration

• Samples: 512 (256 from each dataset)
• Datasets:
  • HuggingFaceH4/ultrachat_200k (train_sft split) — length-filtered (longest conversations selected)
  • nvidia/Nemotron-Post-Training-Dataset-v2 (chat split)
• Max sequence length: 1024
• All experts calibrated: moe_calibrate_all_experts=True

Usage with vLLM

Please use nightly vLLM for support.

vllm serve Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4 \
    --kv-cache-dtype fp8 \
    --reasoning-parser qwen3 \
    --enable-auto-tool-choice \
    --tool-call-parser qwen3_coder

Specs

Same architecture and capabilities as Qwen/Qwen3.5-35B-A3B, including vision (image/video understanding).

Credits

• Uncensoring by HauhauCS
• Base model by Qwen
• NVFP4 quantization and deployment by Li101