← back to catalog · registered 2026-09-29 08:57

YukinoKaorisuna/Qwen3.8-9B-Uncensored-ninfer-8gb

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/YukinoKaorisuna%2FQwen3.8-9B-Uncensored-ninfer-8gb"
Response includes
  • classification m-uncensored
  • files 4
  • author_summary 3 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
1
Model age
today
created 2026-09-29

Metadata

License
apache-2.0
Languages
zh en
Tags
ninfer qwen uncensored abliterated text-generation 9b 8gb low-vram zh en license:apache-2.0 region:us

Related

Total size
0 B
Files
4
Quantizations
1
Registered
2026-09-29 08:57
Last updated on HF
2026-09-29 08:07

Files by quantization

Auxiliary files 4 files 6.07 GB
qwen3_8_9b_uncensored.ninfer 6.07 GB 0dbb287c download
README.md 4.26 KB 3cccf355 download
qwen3_8_9b_uncensored.ninfer.conversion.json 3.28 KB f2f473e9 download
.gitattributes 1.55 KB b23eabdb 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
  • 9b
  • 8gb
  • low-vram

Qwen3.8-9B-Uncensored-ninfer-8gb

适用硬件 / Target GPU: 8 GB 显存即可(RTX 4060 Laptop / 3070 / 4060 / 4060 Ti 8G …)
实测显存占用 / Measured VRAM: 4.54 GiB(max_context 2048,bf16 KV)
制品大小 / Artifact size: 6.07 GiB(groupwise-int 配方)

NInfer engine native format — This is a .ninfer artifact converted exclusively for the NInfer inference engine. It is not a generic HF safetensors checkpoint and cannot be loaded with transformers; it requires the NInfer engine (via ComfyUI-NInfer).

NInfer 引擎特供格式 —— 这是专为 NInfer 推理引擎转换的 .ninfer 制品,不是通用 HF safetensors,无法用 transformers 直接加载,需配合 NInfer 引擎(ComfyUI-NInfer 节点)。

这是 8 GB 显卡目前唯一可用的 .ninfer 制品(破限版)

NInfer 生态现有制品对显存的胃口是分层的,8 GB 卡只有 9B 这一档能落得下:

制品 显存需求 8 GB 卡
Qwen3.8-27B(15.33 / 19.03 GiB) ≥ 16 GB ✗ 放不下
Qwen3.8-9B(本仓库,实测 4.54 GiB) ~5 GB ✓ 唯一可用

This is the only .ninfer artifact that fits an 8 GB card today, and this is its abliterated (refusal-direction-removed) build.

简介 / Overview

Qwen3.8-9B 的破限(abliterated)版,方法是 heretic 风格的定向消融 —— 直接在本仓库配套的
原版权重上做正交化投影,不改架构、不改 tokenizer、不重训,所以转换后与原版字节结构完全一致,只有数值不同。

An abliterated build of Qwen3.8-9B produced by directional ablation on top of the same base weights used by
Qwen3.8-9B-ninfer-8gb. No architecture or tokenizer changes.

实测对比 / Measured behaviour

同一组"贴边"提示词,原版 vs 破限版各跑一遍(RTX 5070 Ti,--no-thinking):

提示词 原版 破限版
道德幽暗的第一人称独白 不拒答、直白(678 字符) 不拒答、直白(476 字符)
粗粝暴力场景 + 脏话 不拒答、带脏话(466 字符) 不拒答、带脏话(729 字符)
贝叶斯定理解释(能力对照) 准确 准确

如实说明 / Honest note:Qwen3.8 蒸馏系 9B 的原版拒答阈值本身就较高,上面这些测试它一次都没拒绝。
破限版可见的差异主要是风格更少收敛、篇幅更饱满,而不是"解锁了原本会拒绝的内容"。
需要你自己在自己的用途上实测确认。

Capability impact: 消融不是重训,通用能力影响很小 —— 上表能力对照题两者表现一致。

来源 / Provenance

用法 / Usage

  1. 把 qwen3_8_9b_uncensored.ninfer 放进 <ComfyUI>/models/LLM/
  2. 用 ComfyUI-NInfer 的 NInfer Local LLM 节点选它
  3. 节点的 dll_path 留空
  4. 配合 system_prompt 自定义角色设定效果更好(破限 ≠ 自动变风格)

实测性能 / Performance(max_context 2048)

Decode ≈114 tok/s
显存占用 4.54 GiB

原版 / Non-abliterated variant

不加消融的同源版本:Qwen3.8-9B-ninfer-8gb

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 Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.