Get the app
← back to catalog · registered 2026-08-29 22:03

Rin247/Qwen3-VL-4B-Uncensored-Aquarion-INT8

Rin247 Qwen 4.0B
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-VL-4B-Uncensored-Aquarion-INT8"
Response includes
  • classification m1
  • files 7
  • hub_downloads_all_time 26
  • author_summary 52 models
  • readme_text full
Try next
GET/models?author=Rin247
All 52 models by Rin247
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
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)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
26
12 last 30d - stable
Likes
1
Model age
6w ago
created 2026-08-29
Downloads over time
Now33→from0↑0%
01224360 on Aug 2933 on Oct 14AugSepOct
Aug 29 → Oct 14 · 47 snapshots · spans 46 days

Metadata

Tags
safetensors qwen3_vl quantized int8 uncensored abliterated 8-bit int8_weight_only region:us

Related

Other by Rin247
Qwen3-VL-8B-Instruct-Uncensored-Aquarion-FP4 129 Qwen3.6-35B-A3B-Uncensored-Aquarion-FP4 127 Qwen3.6-27B-Uncensored-Aquarion-FP4 75 gemma-3-12b-it-Uncensored-Aquarion-INT4 46 Qwen3-VL-4B-Uncensored-Aquarion-INT4 42
Total size
4.50 GB
Files
7
Quantizations
1
Registered
2026-08-29 22:03
Last updated on HF
2026-08-29 21:21
Source huggingface.co/Rin247/Qwen3-VL-4B-Uncensored-Aquarion-INT8 ↗

Files by quantization

Auxiliary files 7 files 4.51 GB
model.safetensors 4.50 GB 7740447d download
tokenizer.json 10.9 MB be756060 download
config.json 20.5 KB 9fb17c1b download
chat_template.jinja 5.29 KB 2a65e88d download
.gitattributes 1.53 KB 52373fe2 download
README.md 828 B fb87f89b download
tokenizer_config.json 724 B c6b8d7a2 download

README current version from Hugging Face

tags:

  • quantized
  • safetensors
  • int8
  • uncensored
  • abliterated

Qwen3 VL 4B Uncensored Aquarion INT8

INT8 weight-only safetensors quantization of Qwen3-VL-4B.

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-VL-4B
  • Format: INT8 (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 INT8 quantized weights9f83ca0799 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.

Get the app Browse the catalog
Open in Abliteration