模型索引 / Qwen / Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
Qwen / MODEL PROFILE

Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

DavidAU 发布 · Heretic · GGUF / MLX / Transformers

模型系列Qwen
参数规模27B
Q4 显存估算约 16.5 GB
近 30 天下载25K
声明的许可证apache-2.0
来源仓库24 个

模型来源

该模型由 DavidAU 在 Hugging Face 发布。本站整理公开仓库元数据,方便检索和比较;模型的具体行为与表现请以发布者说明和实际测试为准。

声明的基座模型

trohrbaugh/Qwen3.6-27B-heretic-ara ↗

硬件与上下文

按 27B 参数、4-bit 权重估算约 16.5 GB 显存。此估算包含 15% 权重开销和 1 GB 基础余量。 KV cache、上下文长度、多模态组件和并发数会增加实际占用。参数量由模型名称解析,未做独立核验。

上下文长度:公开元数据未注明,请查看模型卡。

下载来源与量化版本

24 个仓库
HUGGING FACE 仓库格式近 30 天下载许可证声明
DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF22.3Kapache-2.0
mlx-community/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-OptiQ-4bit ↗MLX466apache-2.0
Gr8white925/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF327apache-2.0
Kasume412/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF264apache-2.0
pablo85318/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF235apache-2.0
pupsipups/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF206apache-2.0
AndreyCodes/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF202apache-2.0
DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking ↗Transformers198apache-2.0
ryryryan/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF170apache-2.0
bernquant/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF ↗GGUF164apache-2.0
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-BF16 ↗MLX44apache-2.0
TheCluster/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-7.6bit ↗MLX43apache-2.0
TheCluster/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit ↗MLX40apache-2.0
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-Text-mxfp4-mlx ↗MLX36apache-2.0
IITheLordII/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4bit ↗MLX35apache-2.0
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-mxfp8-mlx ↗MLX32apache-2.0
IITheLordII/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-3bit ↗MLX29apache-2.0
AutisticAF/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4Bit ↗MLX25apache-2.0
culturerevolt/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit-mlx-4Bit ↗MLX20apache-2.0
nightmedia/Qwen3.6-27B-Polaris-Heretic-mxfp8-mlx ↗MLX18apache-2.0
Dracoform/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4Bit ↗MLX16apache-2.0
nightmedia/Qwen3.6-27B-Polaris-Heretic-mxfp4-mlx ↗MLX16apache-2.0
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-mxfp4-mlx ↗MLX14apache-2.0
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-qx64-hi-mlx ↗MLX12apache-2.0
“无审查”是发布者使用的描述,不代表完全没有拒答,也不代表能力、准确性或安全性的保证。本站未测量拒答率或运行性能基准。

同系列模型

更多 Qwen →