license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF
tags:
- qwen35
- abliterated
- uncensored
- rocmfp4
- halofpx
- gguf
- mtp
library_name: gguf
Qwen3.8-27B-abliterated (ROCmFP4)
ROCmFP4 quantized version of huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF (locally requantized).
- Base model: Qwen3.8-27B (dense) abliterated (refusal behavior removed, uncensored)
- Quantization: Q8_0 → ROCmFP4 (
Q4_0_ROCMFP4_FAST, 4.26 bpw),--allow-requantize - MTP: ✅ model has MTP head — generation speed +~50% when enabled (measured 12-13 → 17-19 t/s)
- Vision: text-only version (vision belongs to Ornith-abliterated — the ROCmFPX engine cannot run MTP and vision simultaneously; see halofpx docs)
⚠ Important: Format Notice
ROCmFP4 is a proprietary quantization format of the halofpx (ROCmFPX) engine — upstream llama.cpp CANNOT load this file!
Load it with halofpx (register this GGUF in the halofpx registry, then POST /api/v1/load).
Files
| File | Size | sha256 |
|---|---|---|
| Qwen3.8-27B-abliterated-Q4_ROCmFPX_FAST.gguf | ~14 GiB | see sha256.txt |
| mmproj-model-bf16.gguf | ~889 MiB | see sha256.txt |
Usage
# After registering in halofpx registry (example):
curl -X POST http://127.0.0.1:8010/api/v1/load \
-H "Authorization: Bearer ***" \
-d '{"model_id":"qwen38-27b-abliterated","reasoning_mode":"off"}'
- Reasoning model:
reasoning_mode: offoutputs directly - MTP enabled in run_config (
mtp_enabled: true) — but MTP + vision simultaneously crashes the engine (known ROCmFPX limitation): use MTP for text-only, use Ornith for vision
Disclaimer
This is an abliterated (uncensored) version and may produce outputs that do not conform to safety policies. Use at your own risk. No warranty is provided.
Qwen3.8-27B-abliterated（ROCmFP4）
基于 huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF 的 ROCmFP4 量化版（本地 requantize 产物）。
- 原模型：Qwen3.8-27B（密集架构）的 abliterated 消融版（去拒绝行为，无审查）
- 量化：Q8_0 → ROCmFP4（Q4_0_ROCMFP4_FAST，4.26 bpw），
--allow-requantize - MTP：✅ 模型带 MTP head，开启后生成速度提升 ~50%（实测 12-13 → 17-19 t/s）
- 视觉：纯文本版（视觉能力归 Ornith-abliterated——ROCmFPX 引擎 MTP 与视觉不可兼得，详见 halofpx 文档）
⚠ 重要：格式说明
ROCmFP4 是 halofpx（ROCmFPX）引擎专属量化格式——上游 llama.cpp 无法加载此文件！
请使用 halofpx 加载（halofpx registry 添加此 GGUF 后 POST /api/v1/load）。
文件
| 文件 | 大小 | sha256 |
|---|---|---|
| Qwen3.8-27B-abliterated-Q4_ROCmFPX_FAST.gguf | ~14 GiB | 见仓库 sha256.txt |
| mmproj-model-bf16.gguf | ~889 MiB | 见仓库 sha256.txt |
使用
# halofpx registry 注册后（例）：
curl -X POST http://127.0.0.1:8010/api/v1/load \
-H "Authorization: Bearer ***" \
-d '{"model_id":"qwen38-27b-abliterated","reasoning_mode":"off"}'
- 思考模型：
reasoning_mode: off直接输出 - MTP 开启（run_config
mtp_enabled: true）——但 MTP + 视觉同时启用会导致引擎崩溃（ROCmFPX 已知限制），纯文本场景开 MTP，视觉场景用 Ornith
免责声明
本模型为 abliterated（消融去审查）版本，可能生成不符合安全政策的输出。使用者自行承担全部责任。本仓库不提供任何保证。