DavidAU 发布 Qwen3.6-27B 多阶段微调模型，ARC-C 突破 700
原标题：DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF
AI 摘要
DavidAU 发布了 Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 模型，这是基于 Qwen3.6-27B 的多阶段微调模型，据称在 8 位和 4 位量化下 ARC-C 得分均超过 700，达到闭源模型水平。该模型在 7 项基准测试中 6 项超过基础模型，并支持视觉、推理和创意写作，提供常规和 MTP 量化版本。
正文节选
--- language: - en - zh license: apache-2.0 tags: - unsloth - fine tune - heretic - uncensored - abliterated - ara - MTP GGUF Quants - Regular GGUF Quants - qwen3.6 - multi-stage tuned - thinking - reasoning - all use cases - coder - creative - creative writing - all genres - story - writing - fiction - roleplaying - bfloat16 - all use cases - multi-stage-tune - multi-state-merge datasets: - DavidAU/Polar-STRICT-Datasets - DavidAU/F451-STRICT-Datasets pipeline_tag: image-text-to-text base_model: