license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated
base_model_relation: quantized
tags:
- qwen3_vl
- vision-language
- abliterated
- uncensored
- safetensors
- comfyui
- int8
- transformers
pipeline_tag: image-text-to-text
library_name: transformers
Huihui-Qwen3-VL-4B-Instruct-abliterated — ComfyUI Edition
This repo packages the huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated Vision-Language Model in two ready-to-use formats for ComfyUI:
| File | Size | Format
| Huihui-Qwen3-VL-4B-Instruct-abliterated.safetensors | 8.88 GiB | bf16
| Huihui-Qwen3-VL-4B-Instruct-abliterated-int8.safetensors | 4.13 GiB | int8
Source / Provenance
- Base model:
huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated(apache-2.0) - Origin model:
Qwen/Qwen3-VL-4B-Instruct - Abliteration: only the text part was processed (not the vision part), so the visual encoder behaves identically to the upstream model.
Quantisation script
The INT8 conversion was done on GPU (NVIDIA RTX 5080) in ~6.5 seconds using Star Nodes' 'Star Ultimate Model Converter' inside ComfyUI desktop.
License & disclaimer
- License: apache-2.0 (inherited from upstream
Qwen/Qwen3-VL-4B-Instruct). - Abliteration notice: This is an uncensored variant. The safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Use with caution. See the upstream model card for the full disclaimer.
- No warranty. Users are solely responsible for any consequences arising from use of this model.