← back to catalog · registered 2026-09-25 17:57

YukinoKaorisuna/Qwen3.8-27B-Uncensored-ninfer

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/YukinoKaorisuna%2FQwen3.8-27B-Uncensored-ninfer"
Response includes
  • classification m-uncensored
  • files 4
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
today
created 2026-09-25

Metadata

License
apache-2.0
Languages
zh en
Tags
ninfer qwen uncensored abliterated text-generation zh en license:apache-2.0 region:us
Total size
0 B
Files
4
Quantizations
1
Registered
2026-09-25 17:57
Last updated on HF
2026-09-25 17:24

Files by quantization

Auxiliary files 4 files 15.3 GB
qwen3_8_27b_uncensored.ninfer 15.3 GB e7ea5a70 download
README.md 5.82 KB 2479df3c download
qwen3_8_27b_uncensored.ninfer.conversion.json 5.39 KB 18934d36 download
.gitattributes 1.55 KB 19e01d23 download

README current version from Hugging Face


license: apache-2.0
language:

  • zh
  • en
    pipeline_tag: text-generation
    tags:
  • ninfer
  • qwen
  • uncensored
  • abliterated
  • text-generation

Qwen3.8-27B-Uncensored-ninfer

NInfer engine native format — This is an abliterated (uncensored) build of Qwen3.8-27B, converted to the .ninfer format exclusively for the NInfer inference engine. It is not a generic HF safetensors checkpoint and cannot be loaded with transformers directly; it requires the NInfer engine.

NInfer 引擎特供格式 —— 这是 Qwen3.8-27B 的 abliterated(去对齐 / 破限)版本,专为 NInfer 推理引擎转换的 .ninfer 格式(不是通用 HF safetensors,无法用 transformers 直接加载)。

简介 / Overview

Qwen3.8-27B 的社区破限版,量化配方 groupwise-int-5080(Q3/Q4/Q5 混合,15.33 GB),适配 16GB 显存的 RTX 5070 Ti / 5080。

An abliterated (refusal-direction-removed) build of Qwen3.8-27B, quantized with the groupwise-int-5080 recipe (mixed Q3/Q4/Q5, 15.33 GB), targeting 16 GB cards (RTX 5070 Ti / 5080).

致谢 / Acknowledgements

站在以下工作之上 / Built on top of:

感谢以上所有作者!Thanks to all authors above!

能力损失 / Capability Impact

破限(abliteration)不是重新训练,而是从权重中"正交化掉拒绝方向"。实测其对通用能力的影响很小,但在竞赛级难题上略有下降。

Abliteration removes the refusal direction rather than retraining. Its impact on general capability is small, with a slight drop on competition-level problems. The numbers below are from a quick in-house test (not an official benchmark).

经过简单测试(自出 48 道客观题,temperature=0,非官方 benchmark)结果:

轮次 Round 官方 Official 破限 Uncensored
基础 12 题 Basic 12 12
中等 12 题 Medium 12 12
竞赛 12 题 Competition 10 9
高中竞赛 12 题 Olympiad 9 8
总计 Total (48) 43 41

结论 / Conclusion:

  • 日常任务(前 24 题:数学、常识、代码、逻辑)零差异 —— 两个模型完全一致。
  • 竞赛难题上破限版少 2 分(约 4%),集中在两类题:① 自指逻辑(说谎者悖论「这句话是假的」)② 递推函数计算(f(x+1)=f(x)+2x+1 求 f(3))。
  • Everyday tasks (first 24: math, common sense, code, logic) show zero difference. On competition problems the uncensored build scores 2 fewer points (~4%), concentrated in two areas: (1) self-referential logic (the liar paradox), (2) recursive function evaluation.

性能表现 / Performance

RTX 5070 Ti(本机实测,16GB / 70 SM / 896 GB/s)

配置 Config prefill decode
8192 ctx + MTP-3 + CUDA graph ~1300 tok/s ~65 tok/s
8192 ctx + vision + MTP-3 ~1600 tok/s ~68–70 tok/s
65536 ctx 纯文本 (text-only) — ~41 tok/s
  • 图片识别(--vision)在 16GB 卡上需把上下文降到 8192(16384 差 85 MB 显存装不下)。
  • Vision on 16 GB cards needs --max-context 8192 (16384 is 85 MB over budget).

RTX 5080(预计 / Expected, 16GB / 84 SM / 960 GB/s)

指标 Metric 预计值 Expected
prefill ~1378 tok/s
decode ~71 tok/s
MTP 接受率 acceptance ~44.7%
  • 5080 比 5070 Ti 多 14 SM、带宽高 7%;decode 是带宽受限、prefill 是算力受限,所以分别 +7% / +6%。显存同为 16GB,vision 的上下文档位与 5070 Ti 相当。
  • The 5080 has 14 more SMs and 7% more bandwidth than the 5070 Ti. Decode is bandwidth-bound and prefill is compute-bound, giving +7% / +6% respectively. VRAM is the same 16 GB, so the vision context ceiling is comparable.

相关仓库 / Related Repositories

文件 / Files

  • qwen3_8_27b_uncensored.ninfer — 主权重 (15.33 GB) / main weights
  • qwen3_8_27b_uncensored.ninfer.conversion.json — 转换元数据 / conversion metadata

使用 / Usage

需要 NInfer 引擎(Windows 版见 ninfer-5070ti)。

Requires the NInfer engine (Windows build: see ninfer-5070ti).

ninfer-serve.exe qwen3_8_27b_uncensored.ninfer --host 127.0.0.1 --port 8100 `
  --max-context 65536 --kv-dtype q4 --spec mtp --draft-tokens 3 --embedding-host `
  --model-id m

图片识别版追加 --vision 并把 --max-context 降到 8192。 / For vision, add --vision and lower --max-context to 8192.

免责声明 / Disclaimer

本模型是社区 abliteration 版本,仅供研究与个人创作用途。请遵守当地法律法规,勿用于生成违法或有害内容。

This is a community abliteration build for research and personal creative use only. Comply with local laws and do not use it to generate illegal or harmful content.

Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in app" button that hands off directly to a local runtime of your choice - Abliteration, LM Studio, or Ollama. No API keys, no subscription, no prompt leakage.