Get the app
← back to catalog · registered 2026-09-26 21:57

TheWirelessPhoenix/Qwen3.5-4B-abliterated-huihui-ai

TheWirelessPhoenix 4B multimodal second-order 
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/TheWirelessPhoenix%2FQwen3.5-4B-abliterated-huihui-ai"
Response includes
  • classification m-uncensored
  • files 10
  • author_summary 9 models
  • readme_text full
Try next
GET/models?author=TheWirelessPhoenix
All 9 models by TheWirelessPhoenix
 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 · 30-day
0
Likes
0
Model age
today
created 2026-09-26

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.

huihui-ai/Huihui-Qwen3.5-4B-abliterated↓ 7,756 this lineage
TheWirelessPhoenix/Qwen3.5-4B-abliterated-huihui-ai

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 abliterated uncensored image-text-to-text conversational base_model:huihui-ai/Huihui-Qwen3.5-4B-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3.5-4B-abliterated license:apache-2.0 4-bit region:us

Related

Other by TheWirelessPhoenix
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 1K DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-mlx_4bit 926 DeepSeek-R1-Distill-Qwen-7B-abliterated-v2-mlx_4bit 773 DeepSeek-R1-Distill-Qwen-7B-abliterated-v2-mlx_8bit 517 Huihui-Qwen3.5-4B-abliterated-oQ4e 444
Same base model
mradermacher/Huihui-Qwen3.5-4B-abliterated-GGUF 20K mradermacher/Huihui-Qwen3.5-4B-abliterated-i1-GGUF 2K darkmaniac7/Qwen3.5-4B-uncensored-MNN 2K Ayaz672i/Huihui-Qwen3.5-4B-Abliterated-PMRA-GGUF 546 Etherealty/Huihui-Qwen3.5-4B-Abliterated-PMRA-GGUF 490
Total size
2.83 GB
Files
10
Quantizations
1
Registered
2026-09-26 21:57
Last updated on HF
2026-09-26 21:54
Source huggingface.co/TheWirelessPhoenix/Qwen3.5-4B-abliterated-huihui-ai ↗ Base model huihui-ai/Huihui-Qwen3.5-4B-abliterated →

Files by quantization

Auxiliary files 10 files 2.84 GB
model.safetensors 2.83 GB 1e342652 download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 99.6 KB 81bd48e6 download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.62 KB 58353d37 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.14 KB 5344df8c download
processor_config.json 991 B 162cd9a2 download
README.md 856 B 5b033a80 download
generation_config.json 115 B 6cd5946d download

README current version from Hugging Face

library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-4B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model: huihui-ai/Huihui-Qwen3.5-4B-abliterated
tags:

  • abliterated
  • uncensored
  • mlx

TheWirelessPhoenix/Qwen3.5-4B-abliterated-huihui-ai

This model was converted to MLX format from huihui-ai/Huihui-Qwen3.5-4B-abliterated
using mlx-vlm version 0.7.3.
Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model TheWirelessPhoenix/Qwen3.5-4B-abliterated-huihui-ai --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
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