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

aesir-unlimited/Qwen3.5-4B-Base40-Uncensored60

aesir-unlimited Qwen 4.7B 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/aesir-unlimited%2FQwen3.5-4B-Base40-Uncensored60"
Response includes
  • classification m-uncensored
  • files 20
  • benchmarks 11 entries
  • hub_downloads_all_time 21
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=aesir-unlimited
All 2 models by aesir-unlimited
 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
21
12 last 30d - active
Likes
0
Descendants
2
in 2 direct forks
Model age
2mo ago
created 2026-08-08
Downloads over time
Now28→from10↑180%
916233010 on Aug 528 on Oct 1128 on Oct 5AugSepOct
Aug 5 → Oct 11 · 50 snapshots · spans 67 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 0.9 UGI
Hazardous 1.2 UGI
Natural Intelligence 13.45 UGI
Political lean -17.3% UGI
Sensitive-Info 11.73 UGI
SocPol 1.5 UGI
UGI 15.32 UGI
Willingness (10) 2.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 3 UGI
Writing 29.68 UGI

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.

Qwen/Qwen3.5-4B this lineage
aesir-unlimited/Qwen3.5-4B-Base40-Uncensored60↓ 12 2 forks
mradermacher/Qwen3.5-4B-Base40-Uncensored60-i1-GGUF↓ 937
mradermacher/Qwen3.5-4B-Base40-Uncensored60-GGUF↓ 693

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text qwen qwen3.5 multimodal model-merge uncensored bfloat16 conversational base_model:Qwen/Qwen3.5-4B

Related

Other by aesir-unlimited
AESIR-Coder-Unfiltered 0
Same base model
huihui-ai/Huihui-Qwen3.5-4B-abliterated 8K insraq/Qwen3.5-4B-EmperoAI-Qwen3.8-Distill-Heretic-Abliterated-MTP-GGUF 6K Andycurrent/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive 3K rodrigomt/Qwen3.5-4B-Uncensored-Aggressive 2K DreamFast/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark 1K
Total size
8.68 GB
Files
20
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-08 14:44
Source huggingface.co/aesir-unlimited/Qwen3.5-4B-Base40-Uncensored60 ↗ Base model Qwen/Qwen3.5-4B ↗

Files by quantization

Auxiliary files 20 files 8.70 GB
model-00006-of-00007.safetensors 1.50 GB 29deb552 download
model-00002-of-00007.safetensors 1.49 GB a8c5356c download
model-00003-of-00007.safetensors 1.49 GB 0853e75c download
model-00001-of-00007.safetensors 1.49 GB db37a57b download
model-00005-of-00007.safetensors 1.48 GB 9f891268 download
model-00007-of-00007.safetensors 751 MB c1bdf1eb download
model-00004-of-00007.safetensors 495 MB d774aa97 download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 65.8 KB dec6bd70 download
tokenizer_config.json 16.3 KB eda48d3e download
LICENSE 11.3 KB f938136e download
chat_template.jinja 7.57 KB a585dec8 download
config.json 2.68 KB 3f0f5ead download
.gitattributes 1.53 KB 52373fe2 download
README.md 941 B 04116038 download
merge_manifest.json 432 B 528de442 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download

README current version from Hugging Face

license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.5-4B
  • rodrigomt/Qwen3.5-4B-Uncensored-Aggressive
    tags:
  • qwen
  • qwen3.5
  • multimodal
  • model-merge
  • uncensored
  • safetensors
  • bfloat16

Qwen3.5-4B Base40 Uncensored60

Multimodal BF16 linear merge of:

Merge formula

merged = 0.40 × Qwen/Qwen3.5-4B + 0.60 × rodrigomt/Qwen3.5-4B-Uncensored-Aggressive

The interpolation was calculated in FP32 and saved as BF16 Safetensors.
Tokenizer, chat-template, image-processor, and video-processor files come from
the official Qwen checkpoint to preserve native multimodal compatibility.

This is an experimental merge and should be evaluated before production use.

README history 1 version

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

  1. 2026-08-08Upload Qwen3.5-4B 40% base / 60% uncensored multimodal mergedbac5fa941 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