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

nico248000000000/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber

nico248000000000 Qwen 28B 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/nico248000000000%2FHuihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 361
  • author_summary 13 models
  • readme_text full
Try next
GET/models?author=nico248000000000
All 13 models by nico248000000000
 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 · lifetime
361
19 last 30d - cooling
Likes
0
Descendants
1
in 1 direct fork
Model age
2mo ago
created 2026-08-08
Downloads over time
Now370→from77↑381%
6217528739977 on Jul 29370 on Oct 11370 on Oct 8JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 days

Genealogy 1 direct fork

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated↓ 717 this lineage
nico248000000000/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber↓ 19 1 fork
nico248000000000/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber-GGUF↓ 86

Variants by this author 2 formats · 105 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Tags
transformers safetensors qwen3_5 image-text-to-text unsloth lora qlora cybersecurity text-generation conversational base_model:huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated base_model:adapter:huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated

Related

Other by nico248000000000
Huihui-Qwen3.8-27B-abliterated-cyber-GGUF 442 Qwen3.8-27B-Uncensored-cyber-GGUF 430 Qwen3.8-27B-Uncensored-FP8-cyber 148 Huihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber-GGUF 86 Huihui-Qwen3.8-27B-abliterated-cyber 80
Same base model
mradermacher/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-i1-GGUF 1K mradermacher/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-GGUF 1K pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-oMLX-MTP 676 sakamakismile/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-NVFP4 353 pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16 206
Total size
51.7 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-08 07:37
Source huggingface.co/nico248000000000/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber ↗ Base model huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated →

Files by quantization

Auxiliary files 12 files 51.8 GB
model-00001-of-00002.safetensors 46.4 GB 6b26f69a download
model-00002-of-00002.safetensors 4.55 GB 3488f485 download
model-base-aux.safetensors 810 MB ecba8ef1 download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 110 KB 306e841f download
tokenizer_config.json 14.9 KB 2a38bcd9 download
chat_template.jinja 7.58 KB a8755d82 download
config.json 4.45 KB 6007eb72 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.16 KB 33818c7f download
README.md 616 B b53d24b0 download
generation_config.json 199 B a84a6755 download

README current version from Hugging Face

library_name: transformers
pipeline_tag: text-generation
base_model: huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated
tags:

  • unsloth
  • lora
  • qlora
  • cybersecurity
  • text-generation

Huihui-ThinkingCap-Qwen3.6-27B-abliterated-cyber

Modèle fusionné 16-bit issu d'un fine-tuning LoRA/QLoRA avec Unsloth.

  • Modèle de base : huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated
  • Domaine : cybersécurité
  • Format : Hugging Face / Transformers
  • Le tokenizer et son chat template sont inclus dans ce dépôt.

La licence et les conditions de redistribution du modèle de base restent applicables.

README history 2 versions

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

  1. 2026-08-08Upload Huihui-ThinkingCap-Qwen3.6-27B-abliterated_merged_16bitfb1a480616 B
    Loading...
  2. 2026-08-08Unsloth Model Card5542945641 B
    Loading...

Discussions 1 thread

  1. 2026-08-11request for info and request for further developmentopen3 💬#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