← back to catalog · registered 2026-11-14 06:03

isichan-ai/YASAKANI_Uncensored_VL

isichan-ai Qwen GGUF multimodal
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/isichan-ai%2FYASAKANI_Uncensored_VL"
Response includes
  • classification m-uncensored
  • files 4
  • author_summary 2 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
1w ago
created 2026-11-14

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Tags
gguf yasakani qwen3.8 mmproj vision base_model:Qwen/Qwen3.8-27B base_model:quantized:Qwen/Qwen3.8-27B license:apache-2.0 region:us

Related

Control vectors

Total size
0 B
Files
4
Quantizations
2
Registered
2026-11-14 06:03
Last updated on HF
2026-11-14 05:58

Files by quantization

BF16 1 file 888 MB
mmproj-Qwen3.8-27B-BF16.gguf 888 MB ******** download
Auxiliary files 3 files 15.0 KB
LICENSE 11.3 KB f938136e download
README.md 2.11 KB 0af0e824 download
.gitattributes 1.63 KB b7a7f754 download

README current version from Hugging Face


license: apache-2.0
base_model: Qwen/Qwen3.8-27B
tags:

  • yasakani
  • qwen3.8
  • mmproj
  • vision
  • gguf

このリポジトリは、yasakani-dev さんの RTX 5090 専用エンジン YASAKANI と、専用モデル Qwen3.8-27B-YASAKANI-quality を使わせていただいて作りました。
こんなに速くて賢いエンジンを公開してくださって、ありがとうございます!!

YASAKANI Uncensored VL

YASAKANI の Qwen3.8-27B で、画像を読ませた時に使った画像用の部品(mmproj)です

RTX 5090 専用エンジン YASAKANI の Qwen3.8-27B に、画像を読ませて測りました。
その時に使った mmproj を置いています。

YASAKANI の配布版(0.1.0)は、まだ画像の入力に対応していません。
作者さんの更新をお待ちください。


ファイル

ファイル 大きさ sha256
mmproj-Qwen3.8-27B-BF16.gguf 931,145,888 バイト de2a49866988ea272c43dc2a43ee2662c25725a717ca5b9059ea420a97f53fe8

ggml-org/Qwen3.8-27B-GGUF の同じ名前のファイルと、中身は同じです(sha256 が一致)。


画像認識の点数

うちの診断(Ver 01.04・RTX 5090)での画像認識の点です。

モデル 画像認識
YASAKANI(Qwen3.8-27B quality)+この mmproj 87.8
YASAKANI Uncensored(自作)+この mmproj 85.7
公式 Qwen3.8-27B BF16(llama.cpp) 89.8

ライセンス

Apache License 2.0(LICENSE)。
元のモデルは Qwen/Qwen3.8-27B(Alibaba Cloud)、GGUF への変換は ggml-org によるものです。

README history 7 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-16 Restore comparison image (media/compare_yasakani_v11_2026-11-15.png) 629e348 1.3 KB
    Loading...
  2. 2026-11-15 Tidy: keep the model, mmproj and required files on top; move the rest to files/ f7e4877 1.3 KB
    Loading...
  3. 2026-11-15 Tidy: short README, remove media image 5820fb9 1.1 KB
    Loading...
  4. 2026-11-15 v0.2: Huihui-Qwen3.8-27B-abliterated converted with the official YASAKANI too... a3f0146 4.4 KB
    Loading...
  5. 2026-11-14 ページを更新 3279a87 3.6 KB
    Loading...
  6. 2026-11-14 README: thanks to yasakani-dev + comparison table f26bfaf 2.1 KB
    Loading...
  7. 2026-11-14 mmproj (Qwen3.8-27B BF16) + README + LICENSE d40d21b 1.5 KB
    Loading...
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.

Open in Abliteration