license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3.8-27B/blob/main/LICENSE language:

• en
• zh
• ru
• es
• fr
• it
• ja
• ko
• af
• de
• ar
• tr
• is
• pl
• sw
• sv
• nl
• he
• id
• uk
• fa
• pa
• pt
• ms
• fi
• el base_model:
• KridgeDookie/Qwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS library_name: mlx tags:
• qwen3.8
• heretic
• abliterated
• uncensored
• decensored
• all use cases
• mixed-precision
• 9bit pipeline_tag: image-text-to-text

Qwen3.8 27B Abliterated Uncensored Philadelphia Class

Quality: quantized (mixed quants per tensor, group size: 32, 6.096 bpw)

Most tensors use 4-bit, 6-bit or 8-bit affine quantization with a group size 32.

Default value for reasoning_effort is set to 'low' to avoid overthinking.

Recommended settings

1. Sampling Parameters: The developers suggest using the following sets of sampling parameters:

   • Thinking Mode: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
   • Instruct (or non-thinking) mode: temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

   For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetition. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.

Source

This model was converted to MLX format from KridgeDookie/Qwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS using mlx-vlm version 0.6.13.