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

ZeroWw/Josiefied-Qwen3-8B-abliterated-v1-GGUF

ZeroWw Qwen 8B GGUF 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/ZeroWw%2FJosiefied-Qwen3-8B-abliterated-v1-GGUF"
Response includes
  • classification m8
  • files 8
  • hub_downloads_all_time 768
  • author_summary 25 models
  • readme_text full
Try next
GET/models?author=ZeroWw
All 25 models by ZeroWw
 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
768
167 last 30d - stable
Likes
0
Model age
17mo ago
created 2025-05-05
Downloads over time
Now840→from0↑0%
03086169240 on Apr 30, 2025840 on Oct 11Apr '25Jul '25Oct '25JanAprJulOct
Apr 30, 2025 → Oct 11 · 115 snapshots · spans 529 days

Metadata

License
mit
Languages
en
Quantizations
F16
Tags
gguf text-generation en license:mit endpoints_compatible region:us conversational

Related

Other by ZeroWw
Qwen3-8B-abliterated-GGUF 418 Meta-Llama-3.1-8B-Instruct-abliterated-GGUF 338 Llama-3.2-3B-Instruct-abliterated-GGUF 221 NeuralDaredevil-8B-abliterated-GGUF 214 Qwen3-4B-abliterated-GGUF 208
Total size
52.2 GB
Files
8
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2025-05-05 21:49
Source huggingface.co/ZeroWw/Josiefied-Qwen3-8B-abliterated-v1-GGUF ↗

Files by quantization

F16 1 file 15.3 GB
Josiefied-Qwen3-8B-abliterated-v1.f16.gguf 15.3 GB ae8a54ad download
Auxiliary files 7 files 36.9 GB
Josiefied-Qwen3-8B-abliterated-v1.q8_0.gguf 9.20 GB b6a0cd04 download
Josiefied-Qwen3-8B-abliterated-v1.q8_p.gguf 8.11 GB 6dfe9fa2 download
Josiefied-Qwen3-8B-abliterated-v1.q6_k.gguf 7.63 GB 683eb681 download
Josiefied-Qwen3-8B-abliterated-v1.q5_k.gguf 6.89 GB 22b95314 download
Josiefied-Qwen3-8B-abliterated-v1.q8q4.gguf 5.11 GB 18a49bd8 download
.gitattributes 1.95 KB b4bc4fb3 download
README.md 339 B 3bb580bb download

README current version from Hugging Face

license: mit
language:

  • en
    pipeline_tag: text-generation

My own (ZeroWw) quantizations.
output and embed tensors quantized to f16.
all other tensors quantized to q5_k or q6_k.

Result:
both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
and they perform as well as the pure f16.

Updated on: Mon May 05, 21:33:23

README history 1 version

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

  1. 2025-05-05Upload folder using huggingface_hub4132a53339 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