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

Rin247/Qwen3-0.6B-Uncensored-Aquarion-FP4

Rin247 Qwen 220M
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-FP4"
Response includes
  • classification m1
  • files 8
  • hub_downloads_all_time 30
  • 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
30
14 last 30d - stable
Likes
0
Model age
6w ago
created 2026-08-29
Downloads over time
Now35→from0↑0%
01326390 on Aug 2935 on Oct 1435 on Oct 13AugSepOct
Aug 29 → Oct 14 · 47 snapshots · spans 46 days

Metadata

Tags
safetensors qwen3 quantized fp4 uncensored abliterated 8-bit fp4_weight_only region:us

Related

Total size
533 MB
Files
8
Quantizations
1
Registered
2026-08-29 21:03
Last updated on HF
2026-08-29 20:25

Files by quantization

Auxiliary files 8 files 544 MB
model.safetensors 533 MB 2e44205e download
tokenizer.json 10.9 MB be756060 download
config.json 10.7 KB 5ee27207 download
chat_template.jinja 4.16 KB b11e13ef download
.gitattributes 1.53 KB 52373fe2 download
README.md 821 B 841e39c4 download
tokenizer_config.json 724 B df142d09 download
generation_config.json 227 B d40f6c71 download

README current version from Hugging Face


tags:

  • quantized
  • safetensors
  • fp4
  • uncensored
  • abliterated

Qwen3 0.6B Uncensored Aquarion FP4

FP4 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: FP4 (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.

  1. 2026-08-29Upload FP4 quantized weights4cb0cf0792 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