Get the app
← back to catalog · registered 2026-08-22 13:56

d3dx9/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-int4-autoround

d3dx9 Qwen 27B 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/d3dx9%2FQwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-int4-autoround"
Response includes
  • classification m3
  • files 2
  • 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 · 30-day
0
Likes
0
Model age
5mo ago
created 2026-05-06
Downloads over time
Now0→from0↑0%
00110 on May 60 on Oct 12MayJunJulAugSepOct
May 6 → Oct 12 · 63 snapshots · spans 159 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.

DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking↓ 190 this lineage
d3dx9/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-int4-autoround

Metadata

License
apache-2.0
Tags
transformers safetensors autoround int4 w4g128 quantized qwen3.6 text-generation base_model:DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking base_model:finetune:DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking license:apache-2.0 endpoints_compatible

Related

Same base model
DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF 108K mlx-community/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-OptiQ-4bit 1K ryryryan/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF 432 pupsipups/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF 372 pablo85318/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF 368
Total size
0 B
Files
2
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-06 12:29
Source huggingface.co/d3dx9/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-int4-autoround ↗ Base model DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking →

Files by quantization

Auxiliary files 2 files 2.26 KB
.gitattributes 1.59 KB f5bdd3f9 download
README.md 692 B ab9d6cc2 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
    tags:
  • autoround
  • int4
  • w4g128
  • quantized
  • qwen3.6
  • text-generation
    library_name: transformers

Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking AutoRound INT4

This is an AutoRound INT4 quantized version of:

DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

Quantization

  • Method: AutoRound
  • Bits: 4
  • Group size: 128
  • Format: AutoRound
  • Source model license: Apache-2.0

Source model

https://huggingface.co/DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

Notes

This repository contains only the quantized derivative model files.

README history 2 versions

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

  1. 2026-05-06Update README.mdb342b4f692 B
    Loading...
  2. 2026-05-06initial commit294f29928 B
    Loading...

Discussions 1 thread

  1. 2026-06-10would be good, but MTP missing :-(open1 💬#1
    Loading...

Continue on Hugging Face →

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