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

richardyoung/Qwen3-8B-Abliterated-GGUF

Name: richardyoung/Qwen3-8B-Abliterated-GGUF
Author: richardyoung

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/richardyoung%2FQwen3-8B-Abliterated-GGUF"

Response includes

classification m8
files 3
hub_downloads_all_time 12,042
author_summary 17 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

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

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.

Downloads · lifetime

12K

7K last 30d - active

Likes

Model age

9mo ago

created 2026-01-09

Downloads over time

Jan 7 → Oct 11 · 80 snapshots · spans 277 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.

richardyoung/Qwen3-8B-Abliterated↓ 556 this lineage

richardyoung/Qwen3-8B-Abliterated-GGUF↓ 6,787

Variants by this author 2 formats · 7K downloads combined

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

richardyoung/Qwen3-8B-Abliterated-GGUF (this) GGUF 7K
richardyoung/Qwen3-8B-Abliterated safetensors 556

Metadata

License

apache-2.0

Quantizations

Q4_K

Files by quantization

Q4_K 1 file 4.68 GB

qwen3-8b-abliterated-Q4_K_M.gguf

4.68 GB

8625e48d

download

Auxiliary files 2 files 2.54 KB

.gitattributes	1.55 KB	341cf173	download
README.md	1017 B	80572fd8	download

README current version from Hugging Face

license: apache-2.0
base_model: richardyoung/Qwen3-8B-Abliterated
tags:

abliterated
uncensored
qwen3
gguf
library_name: llama.cpp

Qwen3-8B-Abliterated-GGUF

GGUF quantized versions of richardyoung/Qwen3-8B-Abliterated.

Available Quantizations

File	Size	Description
qwen3-8b-abliterated-Q4_K_M.gguf	4.7 GB	4-bit quantization (recommended for most use cases)

Usage with Ollama

ollama run hf.co/richardyoung/Qwen3-8B-Abliterated-GGUF:Q4_K_M

Usage with llama.cpp

./llama-cli -m qwen3-8b-abliterated-Q4_K_M.gguf -p "Your prompt here"

About

This is an abliterated version of Qwen3-8B with reduced safety refusals. See the base model for more details on the abliteration process.

Disclaimer

This model is provided for research purposes only. Users are responsible for ensuring ethical use.

README history 2 versions

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

2026-09-26Standardize author sign-off2560f8f1.1 KB
Loading...
2026-01-09Upload README.md with huggingface_hub273c89e1017 B
Loading...