agentionai 发布去审查版 Qwen3.8-Flash-Next GGUF 量化模型
原标题：agentionai/Qwen3.8-Flash-Next-Gyro-abliterated-Huihui-GGUF
AI 摘要
agentionai 在 Hugging Face 发布了基于 huihui-ai 去审查（abliterated）版 Qwen3.8-Flash-Next 的 GGUF 量化模型，提供 Gyro-S、Gyro-M、Gyro-L 三种尺寸，分别面向 32GB 显卡、48GB 显存/64GB 统一内存和 64GB 统一内存设备。该模型采用 trellis 量化类型，需在 Strata、strix-llama.cpp 或 agentionai/llama.cpp 等分支运行，上游 llama.cpp 暂不支持。作者警告去审查后模型可能输出有害内容，不适合公开或无人监督场景。
正文节选
--- base_model: - huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated - huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-v2-GGUF base_model_relation: quantized license: other license_name: qwen-community-1.0 library_name: gguf pipeline_tag: image-text-to-text tags: - gguf - qwen3.8-flash-next - qwen4exp - abliterated - uncensored - experimental - agentionai --- # Qwen3.8-Flash-Next Gyro, abliterated by huihui-ai — GGUF (experimental) **The abliterated Qwen3.8-Flash-Next on a single GPU, in three si