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

PocketWeights/Qwen3-8B-abliterated-GGUF

PocketWeights Qwen 8B GGUF second-order 41K 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/PocketWeights%2FQwen3-8B-abliterated-GGUF"
Response includes
  • classification m8
  • files 8
  • hub_downloads_all_time 1,193
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=PocketWeights
All 5 models by PocketWeights
 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
1K
Likes
0
Model age
2mo ago
created 2026-07-30
Downloads over time
Now2.3K→from90↑2,459%
08411.7K2.5K90 on Jul 292.3K on Oct 11JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 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.

huihui-ai/Qwen3-8B-abliterated↓ 766 this lineage
PocketWeights/Qwen3-8B-abliterated-GGUF↓ 1,353

Metadata

License
apache-2.0
Quantizations
Q4_K Q6_K
Tags
gguf quantized qwen3 abliterated uncensored security-research conversational pocketweights text-generation base_model:huihui-ai/Qwen3-8B-abliterated base_model:quantized:huihui-ai/Qwen3-8B-abliterated license:apache-2.0

Related

Other by PocketWeights
Llama-3.1-8B-Instruct-abliterated-GGUF 423 Gemma-4-12B-agentic-abliterated-GGUF 307 DeepSeek-R1-Llama-8B-Abliterated-GGUF 205 Gliese-Qwen3.5-9B-Abliterated-WebGGUF 152
Same base model
DevQuasar/huihui-ai.Qwen3-8B-abliterated-GGUF 4K ldostadi/Qwen3-8B-abliterated-Q4_K_M-GGUF 1K jfiekdjdk/Qwen3-8B-abliterated-Q5_K_M-GGUF 619 Melvin56/Qwen3-8B-abliterated-GGUF 451 lt275116547/Qwen3-8B-abliterated-GGUF 427
Total size
10.9 GB
Files
8
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-08-27 11:04
Source huggingface.co/PocketWeights/Qwen3-8B-abliterated-GGUF ↗ Base model huihui-ai/Qwen3-8B-abliterated →

Files by quantization

Q6_K 1 file 6.26 GB
Qwen3-8B-abliterated-GGUF-Q6_K.gguf 6.26 GB e43214d1 download
Q4_K 1 file 4.68 GB
Qwen3-8B-abliterated-GGUF-Q4_K_M.gguf 4.68 GB 2058fd9b download
Auxiliary files 6 files 5.67 KB
.gitattributes 1.63 KB 71759c3a download
artifact-manifest.json 1.56 KB 1679d01f download
README.md 1.27 KB 9f79a0e6 download
quantization-meta.json 1.01 KB a87ff962 download
Qwen3-8B-abliterated-GGUF-Q4_K_M.gguf.sha256 104 B e38ba10d download
Qwen3-8B-abliterated-GGUF-Q6_K.gguf.sha256 102 B 2431309f download

README current version from Hugging Face

base_model: huihui-ai/Qwen3-8B-abliterated
library_name: gguf
license: apache-2.0
tags:

  • gguf
  • qwen3
  • abliterated
  • uncensored
  • security-research

⚡ PocketWeights: Qwen3 8B Abliterated

Heavy models, made light. We specialize in high-quality GGUF quantizations optimized for edge devices and gaming laptops.

What is this model?
This is a specialized, uncensored version of Qwen3-8B created using a fast abliteration method to remove refusals. It has zero safety filters and is designed strictly for offline security research, red-teaming, and controlled pentesting environments.

📦 Pick Your Hardware

We bypass the confusing wall of files to provide specific sizes optimized for your hardware:

  • Q4_K_M (Fits 6GB VRAM): The standard. Perfect for RTX 3060/4050.
  • Q6_K (Fits 8GB VRAM): Near-lossless FP16 quality for RTX 4060/3070.

🚀 Quick Start Guide

Option 1: LM Studio (Easiest)

  1. Download & open LM Studio.
  2. In the search bar, type: PocketWeights/Qwen3-8B-abliterated-GGUF.
  3. Select your hardware size, click Download, and hit Play!

Option 2: Ollama

If you have Ollama installed, simply run this command in your terminal:

ollama run hf.co/PocketWeights/Qwen3-8B-abliterated-GGUF:Q4_K_M

README history 3 versions

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

  1. 2026-08-27Update README.md42cf3424.3 KB
    Loading...
  2. 2026-08-03Update README.mde2cb2b41.3 KB
    Loading...
  3. 2026-07-30Add GGUF artifacts (Q4_K_M, Q6_K) @ 2026-07-30T17:53:47.028771+00:00cb5207f1.1 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