← back to catalog · registered 2026-09-29 01:57

leothebella/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P-GGUF

leothebella 27B GGUF 262K ctx
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/leothebella%2FQwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P-GGUF"
Response includes
  • classification m-uncensored
  • files 4
  • hub_downloads_all_time 64
  • 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 · lifetime
64
Likes
0
Model age
7w ago
created 2026-09-29
Downloads over time
Now 748 → from 0 ↑ 0%
0274549823 0 on Sep 29 748 on Nov 22 748 on Nov 21 SepOctNov
Sep 29 → Nov 22 · 55 snapshots · spans 54 days

Metadata

License
apache-2.0
Quantizations
Q6_K
Tags
gguf mirror license:apache-2.0 endpoints_compatible region:us conversational
Total size
24.1 GB
Files
4
Quantizations
3
Registered
2026-09-29 01:57
Last updated on HF
2026-09-29 01:14

Files by quantization

Q6_K 1 file 24.1 GB
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf 24.1 GB 70c8139f download
BF16 1 file 888 MB
mmproj-Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-BF16.gguf 888 MB 5681b690 download
Auxiliary files 2 files 2.77 KB
.gitattributes 1.67 KB a54e85f4 download
README.md 1.11 KB d6c559be download

README current version from Hugging Face


license: apache-2.0
tags: [mirror]

Qwen3.8-27B Uncensored HauhauCS Aggressive Q6_K_P (single-quant mirror)

Single-purpose mirror for Runpod Serverless model caching (which caches a whole repo, so this repo holds
only the files one endpoint loads). Generated by comfyui/tools/mirror.py from manifest.json (chat-uncensored).
All credit and terms belong to the source repositories; the licences below apply unchanged.

  • Apache-2.0 (from HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF)
File Source Size Note
Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf 25.92 GB
mmproj-Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-BF16.gguf HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF/mmproj-Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-BF16.gguf 0.93 GB

README history 1 version

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

  1. 2026-09-29 Update model card 293be02 1.1 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