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

Felldude/Qwen3-VL-4B-Instruct-Uncensored-FP8

Felldude Qwen 4.0B multimodal
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-4B-Instruct-Uncensored-FP8"
Response includes
  • classification m-uncensored
  • files 11
  • benchmarks 11 entries
  • hub_downloads_all_time 3,102
  • 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
3K
293 last 30d - cooling
Likes
10
Model age
3mo ago
created 2026-06-28
Downloads over time
Now3.2K→from173↑1,755%
211.2K2.3K3.5K173 on Jul 13.2K on Oct 11JulAugSepOct
Jul 1 → Oct 11 · 54 snapshots · spans 102 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.3 UGI
Hazardous 1.8 UGI
Natural Intelligence 12.82 UGI
Political lean -16.0% UGI
Sensitive-Info 13.07 UGI
SocPol 1 UGI
UGI 34.55 UGI
Willingness (10) 7.8 UGI
W10-Adherence 8.5 UGI
W10-Direct 7 UGI
Writing 12.55 UGI

Genealogy 0 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.

Qwen/Qwen3-VL-4B-Instruct this lineage
Felldude/Qwen3-VL-4B-Instruct-Uncensored-FP8↓ 293

Variants by this author 2 formats · 444 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Tags
safetensors qwen3_vl fp32 vision qwen qwen3 vl image to text base_model:Qwen/Qwen3-VL-4B-Instruct base_model:finetune:Qwen/Qwen3-VL-4B-Instruct license:apache-2.0 region:us

Related

Other by Felldude
Qwen3-VL-8B-Instruct-Uncensored-V2 621 Ministral-3-8B-Uncensored-FP8 170 Qwen3.5-4B-Uncensored-FP8 156 Qwen3-VL-4B-Instruct-Uncensored 151 Ministral-3-8B-Uncensored 146
Same base model
huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated 15K huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated-FP8 459 Goekdeniz-Guelmez/Josiefied-Qwen3-VL-4B-Instruct-abliterated-beta-v1 380 Felldude/Qwen3-VL-4B-Instruct-Uncensored 151 prithivMLmods/Qwen3-VL-4B-Instruct-abliterated-v1 77
Total size
5.29 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-28 19:13
Source huggingface.co/Felldude/Qwen3-VL-4B-Instruct-Uncensored-FP8 ↗ Base model Qwen/Qwen3-VL-4B-Instruct ↗

Files by quantization

Auxiliary files 11 files 5.30 GB
model.safetensors 5.29 GB 5d824144 download
tokenizer.json 6.71 MB c6cc1014 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 20024bfe download
tokenizer_config.json 10.6 KB d3d37632 download
chat_template.json 5.37 KB e49e75bd download
.gitattributes 1.48 KB a6344aac download
config.json 1.47 KB 22be8bb7 download
README.md 560 B a4b4aab7 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download

README current version from Hugging Face

tags:

  • fp32
  • vision
  • qwen
  • qwen3 vl
  • image to text
    base_model:
  • Qwen/Qwen3-VL-4B-Instruct
    license: apache-2.0

Qwen3-VL-4B-Instruct-Uncensored-FP8

NOTE: Do Not quantize this model use the full FP32 Training when quantizing https://huggingface.co/Felldude/Qwen3-VL-4B-Instruct-Uncensored

This model has been finetuned with image and text pairs at 1024px and shows high affinity with limited hallucination on NSFW task.

Full FP32 Training with blockwise conversion to FP8 (Key Blocks in FP32)

This model has limited video caption ability.

README history 5 versions

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

  1. 2026-06-28Update README.mdb007197560 B
    Loading...
  2. 2026-06-28Update README.md630a67e560 B
    Loading...
  3. 2026-06-28Update README.mdb65e8fb559 B
    Loading...
  4. 2026-06-28Update README.md8516726415 B
    Loading...
  5. 2026-06-28initial commit01a57b828 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