Get the app
← back to catalog · registered 2026-09-04 08:03

AvatarAndrey/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

AvatarAndrey Qwen 27B 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/AvatarAndrey%2FQwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF"
Response includes
  • classification m3
  • files 4
  • hub_downloads_all_time 279
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m3
Sibling qwen models · same method
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
279
188 last 30d - active
Likes
0
Model age
6w ago
created 2026-09-04
Downloads over time
Now414→from0↑0%
01523044550 on Sep 4414 on Oct 21SepOct
Sep 4 → Oct 21 · 48 snapshots · spans 47 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.

Qwen/Qwen3.8-27B this lineage
AvatarAndrey/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF↓ 188

Metadata

License
apache-2.0
Quantizations
Q3_K
Tags
gguf qwen3 abliterated image-text-to-text base_model:Qwen/Qwen3.8-27B base_model:quantized:Qwen/Qwen3.8-27B license:apache-2.0 region:us

Related

Same base model
JonathanColetti/Qwen3.8-27B-Uncensored-GGUF 2.5M huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF 2.4M HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF 2.4M 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 1.1M azukivc/Qwen3.8-27B-Uncensored-GGUF 129K
Total size
11.7 GB
Files
4
Quantizations
3
Registered
2026-09-04 08:03
Last updated on HF
2026-09-04 07:56
Source huggingface.co/AvatarAndrey/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF ↗ Base model Qwen/Qwen3.8-27B ↗

Files by quantization

Q3_K 1 file 11.7 GB
RVN-Q3_K_S-multilingual-mtp.gguf 11.7 GB 221249e7 download
Q8_0 1 file 600 MB
mmproj-Qwen3.8-27B-Q8_0.gguf 600 MB 2e968a6a download
Auxiliary files 2 files 2.85 KB
.gitattributes 1.61 KB 9e93bb16 download
README.md 1.23 KB 82a55a8b download

README current version from Hugging Face

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

  • gguf
  • qwen3
  • abliterated
  • image-text-to-text

Qwen3.8-27B Heretic Abliterated (GGUF) - personal mirror

A pinned personal copy of two files needed to run this model with vision.
Nothing was re-quantized or modified: both files are byte-identical to their
sources (verified by LFS sha256).

file size copied from source revision
RVN-Q3_K_S-multilingual-mtp.gguf 11.7 GiB 0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF 20b94f0613b632b4848bbe3b1e05d9ee0c2b1608
mmproj-Qwen3.8-27B-Q8_0.gguf 600 MiB ggml-org/Qwen3.8-27B-GGUF 0669b98607d47046c7c2b3f801011d54a08cfccf

The weights are the abliterated build; the multimodal projector (mmproj) comes
from the official ggml-org repo. Both are required together - the projector alone
does nothing, and the weights alone give you a text-only model.

Usage

llama-server -m RVN-Q3_K_S-multilingual-mtp.gguf              --mmproj mmproj-Qwen3.8-27B-Q8_0.gguf

Mirrored 2026-09-04. Licensed Apache-2.0, same as both sources.

README history 1 version

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

  1. 2026-09-04README: what this mirror is and where it came from5956f821.2 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