Qwen3.6-27B-TIES

Qwen3.6-27B-TIES

This is a merge of pre-trained language models created using mergekit.

The goal was to improve reasoning, tool use, and voice/prose while removing self-censorship. Currently untested.

Merge Details

Merge Method

This model was merged using the TIES merge method using huihui-ai/Huihui-Qwen3.6-27B-abliterated as a base.

Models Merged

The following models were included in the merge:

• kai-os/Carnice-V2-27b
• darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic
• TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
• llmfan46/Qwen3.6-27B-uncensored-heretic-v2
• nbeerbower/Huihui-Qwen3.6-27B-abliterated-Athanorlite-ORPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: kai-os/Carnice-V2-27b
    parameters:
      weight: 1
      density: 1
  - model: llmfan46/Qwen3.6-27B-uncensored-heretic-v2
    parameters:
      weight: 1
      density: 1
  - model: darkc0de/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-heretic
    parameters:
      weight: 1
      density: 1
  - model: TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
    parameters:
      weight: 1
      density: 1
  - model: nbeerbower/Huihui-Qwen3.6-27B-abliterated-Athanorlite-ORPO
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: huihui-ai/Huihui-Qwen3.6-27B-abliterated
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16