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

Aragduhl/Huihui-Qwen3-VL-8B-Instruct-abliterated-comfy

Aragduhl Qwen 8B multimodal second-order
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/Aragduhl%2FHuihui-Qwen3-VL-8B-Instruct-abliterated-comfy"
Response includes
  • classification m1
  • files 3
  • author_summary 1 models
  • readme_text full
Try next
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 · 30-day
0
Likes
1
Descendants
3
in 3 direct forks
Model age
2mo ago
created 2026-08-05
Downloads over time
Now0→from0↑0%
00110 on Aug 50 on Oct 11AugSepOct
Aug 5 → Oct 11 · 50 snapshots · spans 67 days

Genealogy 3 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-VL-8B-Instruct-abliterated↓ 32,774 this lineage
Aragduhl/Huihui-Qwen3-VL-8B-Instruct-abliterated-comfy 3 forks
C0D3XL1TT3R4RUM/Huihui-Qwen3-VL-8B-Instruct-abliterated-ComfyUI-NVFP4
C0D3XL1TT3R4RUM/Qwen3-VL-8B-abliterated-NVFP4-ComfyUI
paralaif/Huihui-Qwen3-VL-8B-Instruct-abliterated-comfy-int8-convrot

Metadata

License
apache-2.0
Tags
transformers qwen3-vl abliterated uncensored comfyui image-text-to-text base_model:huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated base_model:finetune:huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated license:apache-2.0 endpoints_compatible region:us

Related

Same base model
mradermacher/Huihui-Qwen3-VL-8B-Instruct-abliterated-GGUF 19K noctrex/Huihui-Qwen3-VL-8B-Instruct-abliterated-GGUF 9K mradermacher/Huihui-Qwen3-VL-8B-Instruct-abliterated-i1-GGUF 4K noctrex/Huihui-Qwen3-VL-8B-Instruct-abliterated-i1-GGUF 785 porpgel/Huihui-Qwen3-VL-8B-Instruct-abliterated-Q4_K_M-GGUF 301
Total size
16.3 GB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-05 18:19
Source huggingface.co/Aragduhl/Huihui-Qwen3-VL-8B-Instruct-abliterated-comfy ↗ Base model huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated →

Files by quantization

Auxiliary files 3 files 16.3 GB
Huihui-Qwen3-VL-8B-Instruct-abliterated.safetensors 16.3 GB 97c230fa download
.gitattributes 1.54 KB a30684a1 download
README.md 1.06 KB 200aa033 download

README current version from Hugging Face

license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated
library_name: transformers
pipeline_tag: image-text-to-text
tags:

  • qwen3-vl
  • abliterated
  • uncensored
  • comfyui

Huihui Qwen3-VL-8B Instruct (Abliterated) — ComfyUI Single File

Single-file merge of the four shards of
huihui-ai/Huihui-Qwen3-VL-8B-Instruct-abliterated,
packaged for ComfyUI's native Generate Text node.

  • Format: single transformers-format safetensors (750 tensors)
  • Full vision tower + LM head included
  • Abliterated (uncensored)

ComfyUI usage

  1. Download and place the file in ComfyUI/models/text_encoders/.
  2. In the CLIPLoader node select:
    • clip_name: Huihui-Qwen3-VL-8B-Instruct-abliterated.safetensors
    • type: joyimage (routes to the qwen3vl_8b text encoder)
  3. Feed its CLIP output into a Generate Text node.

Download

hf download Aragduhl/Huihui-Qwen3-VL-8B-Instruct-abliterated-comfy --include "*.safetensors" --local-dir models/text_encoders/

README history 1 version

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

  1. 2026-08-05Upload README.md with huggingface_hub137e6391.1 KB
    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