← back to catalog · registered 2026-08-29 21:03

Rin247/Qwen3-0.6B-Uncensored-Aquarion-FP8

Name: Rin247/Qwen3-0.6B-Uncensored-Aquarion-FP8
Author: Rin247

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%2FQwen3-0.6B-Uncensored-Aquarion-FP8"

Response includes

classification m1
files 8
hub_downloads_all_time 27
author_summary 52 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

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

FromArditi et al. (2024) ↗

Confidence

MEDIUM

Why we say so

primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)

Downloads · lifetime

10 last 30d - stable

Likes

Model age

6w ago

created 2026-08-29

Downloads over time

Aug 29 → Oct 14 · 47 snapshots · spans 46 days

Metadata

Files by quantization

Auxiliary files 8 files 728 MB

model.safetensors	717 MB	17cee608	download
tokenizer.json	10.9 MB	be756060	download
config.json	10.7 KB	c843350b	download
chat_template.jinja	4.16 KB	b11e13ef	download
.gitattributes	1.53 KB	52373fe2	download
README.md	821 B	0536474e	download
tokenizer_config.json	724 B	df142d09	download
generation_config.json	227 B	d40f6c71	download

README current version from Hugging Face

tags:

quantized
safetensors
fp8
uncensored
abliterated

Qwen3 0.6B Uncensored Aquarion FP8

FP8 weight-only safetensors quantization of Qwen3-0.6B.

Aquarion Forge

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

Quantization Details

Base model: Qwen3-0.6B
Format: FP8 (weight-only safetensors)
Method: PyTorch RTN quantization on CPU; scales stored alongside weights
Files: model.safetensors + config.json (contains quantization_config)

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.

2026-08-29Upload FP8 quantized weights8894b9d792 B
Loading...

Rin247/Qwen3-0.6B-Uncensored-Aquarion-FP8

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now