Get the app
← back to catalog · registered 2026-08-22 13:56

Felldude/Qwen3-VL-8B-Instruct-Uncensored

Felldude Qwen 8.8B
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/Felldude%2FQwen3-VL-8B-Instruct-Uncensored"
Response includes
  • classification m-uncensored
  • files 11
  • hub_downloads_all_time 493
  • author_summary 14 models
  • readme_text full
Try next
GET/models?author=Felldude
All 14 models by Felldude
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · lifetime
493
149 last 30d - stable
Likes
2
Descendants
2
in 2 direct forks
Model age
7mo ago
created 2026-03-12
Downloads over time
Now533→from46↑1,059%
2220839558246 on Mar 11533 on Oct 12MarAprMayJunJulAugSepOct
Mar 11 → Oct 12 · 71 snapshots · spans 215 days

Genealogy 2 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.

Felldude/Qwen3-VL-8B-Instruct-Uncensored↓ 149 2 forks
mradermacher/Qwen3-VL-8B-Instruct-Uncensored-GGUF↓ 1,402
mradermacher/Qwen3-VL-8B-Instruct-Uncensored-i1-GGUF↓ 576

Metadata

License
apache-2.0
Languages
en es ja
Tags
safetensors qwen3_vl en es ja license:apache-2.0 region:us

Related

Other by Felldude
Qwen3-VL-8B-Instruct-Uncensored-V2 637 Qwen3-VL-4B-Instruct-Uncensored-FP8 276 Ministral-3-8B-Uncensored-FP8 158 Qwen3.5-4B-Uncensored-FP8 157 Qwen3-VL-4B-Instruct-Uncensored 152
Total size
16.3 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-18 22:43
Source huggingface.co/Felldude/Qwen3-VL-8B-Instruct-Uncensored ↗

Files by quantization

Auxiliary files 11 files 16.3 GB
model.safetensors 16.3 GB 81ff1388 download
tokenizer.json 6.71 MB c6cc1014 download
vocab.json 2.65 MB 4783fe10 download
tokenizer_config.json 10.6 KB d3d37632 download
chat_template.json 5.37 KB 1081bacf download
.gitattributes 1.48 KB a6344aac download
config.json 1.44 KB 0e2df614 download
README.md 786 B 46d79fe8 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 269 B e116347d download

README current version from Hugging Face

license: apache-2.0
language:

  • en
  • es
  • ja

Notes

Version 2 should be used for captioning this version should be used only for a uncensored base training starting point.
https://huggingface.co/Felldude/Qwen3-VL-8B-Instruct-Uncensored-V2

This version requires 24GB or more VRAM.

  • Full finetune of the 8B parameter model (vision encoder frozen).
  • Training used Adam8bit due to model size (BF16/TF32 otherwise).
  • If used for NSFW captioning, leaving the prompt unchanged is recommended.

Prompt

Describe this image in natural language. Analyze the picture carefully and describe all objects, colors, and context. Describe any sexually explicit images as accurately as possible without adding bias such as calling them controversial or inappropriate.

README history 4 versions

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

  1. 2026-03-18Update README.mda1150f2786 B
    Loading...
  2. 2026-03-13Update README.md4d05993598 B
    Loading...
  3. 2026-03-13Update README.md4726e0b576 B
    Loading...
  4. 2026-03-12initial commit3282dd428 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