← back to catalog · registered 2026-08-31 07:03

Rin247/Qwen3.6-27B-Uncensored-Aquarion-FP4

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/Rin247%2FQwen3.6-27B-Uncensored-Aquarion-FP4"
Response includes
  • classification m1
  • files 8
  • hub_downloads_all_time 283
  • author_summary 52 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
283
65 last 30d - stable
Likes
0
Model age
6w ago
created 2026-08-31
Downloads over time
Now317→from0↑0%
01162323490 on Aug 31317 on Oct 18AugSepOct
Aug 31 → Oct 18 · 49 snapshots · spans 48 days

Metadata

Tags
transformers safetensors qwen3_5_text text-generation quantized fp4 uncensored abliterated conversational endpoints_compatible 8-bit fp4_weight_only

Related

Total size
17.5 GB
Files
8
Quantizations
1
Registered
2026-08-31 07:03
Last updated on HF
2026-08-31 11:51

Files by quantization

Auxiliary files 8 files 17.5 GB
model.safetensors 17.5 GB f0e6d03f download
tokenizer.json 19.1 MB 225fe96e download
config.json 34.8 KB 4d338ce9 download
chat_template.jinja 7.73 KB c35a00bc download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.13 KB c487bad4 download
README.md 748 B 3cef8f5b download
generation_config.json 227 B a5baa6a6 download

README current version from Hugging Face


tags:

  • quantized
  • safetensors
  • fp4
  • uncensored
  • abliterated
    library_name: transformers

Qwen3.6-27B-Uncensored-Aquarion-FP4

FP4 weight-only safetensors quantization of Qwen3.6-27B-Uncensored.

Aquarion Forge

This model was abliterated (uncensored) via orthogonal projection of the
refusal direction before quantization — part of the Aquarion forge.

Quantization Details

  • Base model: Qwen3.6-27B-Uncensored
  • Format: FP4 (weight-only safetensors)
  • Method: PyTorch RTN quantization on CPU; scales stored alongside weights

Loading

These use custom weight-only recipes. Dequantize with the matching scale/shape
buffers (*.weight_scale, *.weight_shape) before feeding to an inference engine.

README history 1 version

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

  1. 2026-08-31Upload FP4 quantized weightsfce99c2735 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