Get the app
← back to catalog · registered 2026-09-25 20:57

mradermacher/Qwen3.8-27B-RANA-abliterated-GGUF

mradermacher 27B GGUF 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/mradermacher%2FQwen3.8-27B-RANA-abliterated-GGUF"
Response includes
  • classification m8
  • files 6
  • hub_downloads_all_time 887
  • author_summary 3529 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3529 models by mradermacher
 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)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
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
887
Likes
0
Model age
6w ago
created 2026-09-25
Downloads over time
Now2.2K→from0↑0%
08181.6K2.5K0 on Sep 252.2K on Nov 10SepOctNov
Sep 25 → Nov 10 · 47 snapshots · spans 46 days

Variants by this author 2 formats · 3K downloads combined

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

Metadata

Quantizations
Q2_K Q4_K
Tags
transformers gguf abliteration abliterated uncensored qwen3.8 refusal-direction qwen3 vision-language abliterant en base_model:abliterant/Qwen3.8-27B-RANA-abliterated

Related

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.7M Qwen3-VL-8B-Instruct-abliterated-GGUF 597K Huihui-Qwen3.5-9B-abliterated-GGUF 407K DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF 315K DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF 249K
Total size
24.9 GB
Files
6
Quantizations
5
Registered
2026-09-25 20:57
Last updated on HF
2026-10-17 05:29
Source huggingface.co/mradermacher/Qwen3.8-27B-RANA-abliterated-GGUF ↗

Files by quantization

Q4_K 1 file 14.7 GB
Qwen3.8-27B-RANA-abliterated.Q4_K_S.gguf 14.7 GB 68466041 download
Q2_K 1 file 10.1 GB
Qwen3.8-27B-RANA-abliterated.Q2_K.gguf 10.1 GB 4f432fe9 download
F16 1 file 885 MB
Qwen3.8-27B-RANA-abliterated.mmproj-f16.gguf 885 MB c2ddc420 download
Q8_0 1 file 600 MB
Qwen3.8-27B-RANA-abliterated.mmproj-Q8_0.gguf 600 MB 3f8432fc download
Auxiliary files 2 files 2.16 KB
.gitattributes 1.79 KB 6edadc08 download
README.md 381 B cd8c2b26 download

README current version from Hugging Face

README history 7 versions

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

  1. 2026-10-17auto-patch README.md1a8b8294.1 KB
    Loading...
  2. 2026-10-05auto-patch README.mdc38ee654.1 KB
    Loading...
  3. 2026-09-25auto-patch README.md254811e4.1 KB
    Loading...
  4. 2026-09-25auto-patch README.mdbfa8e9b4.2 KB
    Loading...
  5. 2026-09-25auto-patch README.mdb010c244 KB
    Loading...
  6. 2026-09-25auto-patch README.mdfb90da03.9 KB
    Loading...
  7. 2026-09-25uploaded from marco922dd39381 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