Rin247/Qwen3-4B-Uncensored-Aquarion-INT4

Qwen3 4B Uncensored Aquarion INT4

INT4 weight-only safetensors quantization of Qwen3-4B.

Aquarion Forge

This model was abliterated (uncensored) via orthogonal projection of the refusal direction before quantization — part of the Genesis of Aquarion forge.

Quantization Details

• Base model: Qwen3-4B
• Format: INT4 (weight-only safetensors)
• Method: PyTorch RTN quantization on CPU; scales stored alongside weights
• Files: model.safetensors + config.json (contains quantization_config)

Loading

These use custom weight-only recipes. Dequantize with the matching scale/shape buffers (*.weight_scale, *.weight_shape) before feeding to an inference engine.