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

Stabhappy/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF

Stabhappy Qwen 27B GGUF second-order 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/Stabhappy%2FQwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF"
Response includes
  • classification m3
  • files 7
  • benchmarks 11 entries
  • hub_downloads_all_time 1,459
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Stabhappy
All 2 models by Stabhappy
 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
1K
460 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-05-17
Downloads over time
Now1.6K→from590↑175%
4658881.3K1.7K590 on May 201.6K on Oct 11MayJunJulAugSepOct
May 20 → Oct 11 · 60 snapshots · spans 144 days

Benchmarks

Benchmark Score Source
Entertainment 1.7 UGI
Hazardous 2.4 UGI
Natural Intelligence 26.28 UGI
Political lean -26.8% UGI
Sensitive-Info 18.31 UGI
SocPol 1.6 UGI
UGI 43.88 UGI
Willingness (10) 9.5 UGI
W10-Adherence 10 UGI
W10-Direct 9 UGI
Writing 38.41 UGI

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.

llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved↓ 261 this lineage
Stabhappy/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF↓ 460

Metadata

Quantizations
Q4_K Q5_K Q6_K Q8_0
Tags
gguf base_model:llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved base_model:quantized:llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved endpoints_compatible region:us conversational

Related

Other by Stabhappy
Qwen3.6-27B-abliterated-GGUF 124
Same base model
llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF 5K mradermacher/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-i1-GGUF 1K magiccodingman/Qwen3.6-27B-Uncensored-MagicQuant-MTP-GGUF 1K llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-NVFP4-GGUF 617 mradermacher/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF 571
Total size
81.8 GB
Files
7
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2026-05-17 06:55
Source huggingface.co/Stabhappy/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF ↗ Base model llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved →

Files by quantization

Q8_0 1 file 27.1 GB
llmfan46_qwen3.6_27b_uncensored_heretic_v2_native_mtp_preserved-Q8_0.gguf 27.1 GB 96e8632d download
Q6_K 1 file 20.9 GB
llmfan46_qwen3.6_27b_uncensored_heretic_v2_native_mtp_preserved-Q6_K.gguf 20.9 GB 6c7c016f download
Q5_K 1 file 18.2 GB
llmfan46_qwen3.6_27b_uncensored_heretic_v2_native_mtp_preserved-Q5_K_M.gguf 18.2 GB f2af7199 download
Q4_K 1 file 15.7 GB
llmfan46_qwen3.6_27b_uncensored_heretic_v2_native_mtp_preserved-Q4_K_M.gguf 15.7 GB 9f7c0723 download
F16 1 file 885 MB
mmproj-llmfan46_qwen3.6_27b_uncensored_heretic_v2_native_mtp_preserved-f16.gguf 885 MB 6c5233eb download
Auxiliary files 2 files 2.22 KB
.gitattributes 2.03 KB 1e316716 download
README.md 197 B 7cef2466 download

README current version from Hugging Face

base_model:

  • llmfan46/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved

Created with llama.cpp build b9174 (MTP official support)

use

--spec-type draft-mtp
--spec-draft-n-max 3 \

README history 3 versions

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

  1. 2026-05-17Update README.md909a085197 B
    Loading...
  2. 2026-05-17Update README.md109bb2a144 B
    Loading...
  3. 2026-05-17Create README.mded162e085 B
    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