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

azminawwar/huihui-ai_Huihui-Qwen3.5-0.8B-abliterated_Ultimate-Offensive-Red-Team

azminawwar Qwen 800M GGUF multimodal 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/azminawwar%2Fhuihui-ai_Huihui-Qwen3.5-0.8B-abliterated_Ultimate-Offensive-Red-Team"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 3,689
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=azminawwar
All 2 models by azminawwar
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
4K
2K last 30d - active
Likes
3
Model age
2mo ago
created 2026-08-02
Downloads over time
Now4.7K→from646↑622%
4452K3.5K5.1K646 on Aug 54.7K on Oct 11AugSepOct
Aug 5 → Oct 11 · 50 snapshots · spans 67 days

Metadata

Quantizations
BF16 F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf qwen3_5 llama.cpp unsloth vision-language-model endpoints_compatible region:us conversational

Related

Other by azminawwar
Huihui-Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k 757
Total size
6.24 GB
Files
12
Quantizations
10
Registered
2026-08-22 13:56
Last updated on HF
2026-08-02 03:04
Source huggingface.co/azminawwar/huihui-ai_Huihui-Qwen3.5-0.8B-abliterated_Ultimate-Offensive-Red-Team ↗

Files by quantization

BF16 1 file 1.45 GB
Huihui-Qwen3.5-0.8B-abliterated.BF16.gguf 1.45 GB 28d4684a download
F16 1 file 1.45 GB
Huihui-Qwen3.5-0.8B-abliterated.F16.gguf 1.45 GB ec7644d2 download
Q8_0 1 file 795 MB
Huihui-Qwen3.5-0.8B-abliterated.Q8_0.gguf 795 MB f3dd2ddd download
Q6_K 1 file 617 MB
Huihui-Qwen3.5-0.8B-abliterated.Q6_K.gguf 617 MB b8143dd3 download
Q5_K 1 file 565 MB
Huihui-Qwen3.5-0.8B-abliterated.Q5_K_M.gguf 565 MB 2e1cb8d1 download
Q4_K 1 file 517 MB
Huihui-Qwen3.5-0.8B-abliterated.Q4_K_M.gguf 517 MB 7388c883 download
Q2_K 1 file 469 MB
Huihui-Qwen3.5-0.8B-abliterated.Q2_K_L.gguf 469 MB 9ec36895 download
Q3_K 1 file 454 MB
Huihui-Qwen3.5-0.8B-abliterated.Q3_K_M.gguf 454 MB a8bedceb download
mmproj 1 file 195 MB
Huihui-Qwen3.5-0.8B-abliterated.F16-mmproj.gguf 195 MB 33a9eb40 download
Auxiliary files 3 files 6.48 KB
config.json 3.08 KB 24b61ca7 download
.gitattributes 2.18 KB 56d5e8d6 download
README.md 1.21 KB 63c0d2f1 download

README current version from Hugging Face

tags:

  • gguf
  • llama.cpp
  • unsloth
  • vision-language-model

huihui-ai_Huihui-Qwen3.5-0.8B-abliterated_Ultimate-Offensive-Red-Team : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf azminawwar/huihui-ai_Huihui-Qwen3.5-0.8B-abliterated_Ultimate-Offensive-Red-Team --jinja
  • For multimodal models: llama-mtmd-cli -hf azminawwar/huihui-ai_Huihui-Qwen3.5-0.8B-abliterated_Ultimate-Offensive-Red-Team --jinja

Available Model files:

  • Huihui-Qwen3.5-0.8B-abliterated.Q2_K_L.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.F16.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.Q3_K_M.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.Q4_K_M.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.Q5_K_M.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.Q6_K.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.Q8_0.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.BF16.gguf
  • Huihui-Qwen3.5-0.8B-abliterated.F16-mmproj.gguf
    This was trained 2x faster with Unsloth

README history 1 version

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

  1. 2026-08-02Add README7eed7831.2 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