Get the app
← back to catalog · registered 2026-08-30 09:03

DogOnKeyboard/Qwen3.8-27B-Uncensored-NInfer

DogOnKeyboard Qwen 27B multimodal second-order
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/DogOnKeyboard%2FQwen3.8-27B-Uncensored-NInfer"
Response includes
  • classification m1
  • files 3
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · 30-day
0
Likes
0
Model age
6w ago
created 2026-08-30
Downloads over time
Now0→from0↑0%
00110 on Aug 300 on Oct 14AugSepOct
Aug 30 → Oct 14 · 46 snapshots · spans 45 days

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.

JonathanColetti/Qwen3.8-27B-Uncensored↓ 27,186 this lineage
DogOnKeyboard/Qwen3.8-27B-Uncensored-NInfer

Metadata

License
apache-2.0
Languages
en zh
Tags
transformers ninfer qwen3.8 uncensored abliterated vision mtp image-text-to-text en zh base_model:JonathanColetti/Qwen3.8-27B-Uncensored base_model:finetune:JonathanColetti/Qwen3.8-27B-Uncensored

Related

Same base model
twolven/Qwen3.8-27B-abliterated-AWQ-MTP 45K zerodigest/Qwen3.8-27B-Uncensored-YMQ-MTP-GGUF 14K joshebbs/qwen3.8-27b-uncensored-nvfp4-modelopt 13K mradermacher/Qwen3.8-27B-Uncensored-GGUF 10K quuyy/Qwen3.8-27B-Uncensored-GGUF 5K
Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-30 09:03
Last updated on HF
2026-08-30 08:51
Source huggingface.co/DogOnKeyboard/Qwen3.8-27B-Uncensored-NInfer ↗ Base model JonathanColetti/Qwen3.8-27B-Uncensored →

Files by quantization

Auxiliary files 3 files 17.0 GB
qwen3_8_27b_uncensored.ninfer 17.0 GB 714565ed download
.gitattributes 1.55 KB 19e01d23 download
README.md 767 B 2d672a10 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • JonathanColetti/Qwen3.8-27B-Uncensored
    pipeline_tag: image-text-to-text
    library_name: transformers
    language:
  • en
  • zh
    tags:
  • ninfer
  • qwen3.8
  • uncensored
  • abliterated
  • vision
  • mtp

Qwen3.8-27B-Uncensored — NInfer

This repository contains JonathanColetti/Qwen3.8-27B-Uncensored converted to the native NInfer .ninfer artifact format.

The model weights, architecture, and generation behavior are preserved from the source — the only change is the container format: the 12-file safetensors distribution (plus the MTP block) is packed into a single self-contained .ninfer artifact for direct use with the NInfer runtime.

README history 4 versions

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

  1. 2026-08-30Update README.md807a42b767 B
    Loading...
  2. 2026-08-30Update README.md4f9ad03767 B
    Loading...
  3. 2026-08-30Update README.md58a6256767 B
    Loading...
  4. 2026-08-30Add model card51725582.9 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.

Get the app Browse the catalog
Open in Abliteration