Qwen3.5 9B-class abliterated variant
Captured configuration records Qwen3_5ForConditionalGeneration with model type qwen3_5 and about 9.65B parameters, described as an uncensored abliteration of Qwen/Qwen3.5-9B.
Open Source Model Profile · huihui-ai
Huihui-Qwen3.5-9B-abliterated
Huihui-Qwen3.5-9B-abliterated is a 9.65B-parameter Qwen3.5 model from huihui-ai. According to the model card, it is an uncensored abliterated version of Qwen/Qwen3.5-9B.
- Publisher
- huihui-ai
- Task
- image-text-to-text
- Model type
- qwen3_5
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Huihui-Qwen3.5-9B-abliterated is published by huihui-ai as an image-text-to-text model. Captured metadata reports 9,653,104,368 parameters with Qwen3_5ForConditionalGeneration, and card data records apache-2.0. According to the model card, it is an uncensored abliterated version of Qwen/Qwen3.5-9B built as a crude proof-of-concept refusal-removal implementation.
Recorded capabilities
Apache-2.0 multimodal record
Card data records apache-2.0, and hub tags mark image-text-to-text with abliterated and uncensored markers.
Explicit safety and legal warnings
According to the model card, reduced safety filtering creates sensitive-output, audience, and legal-ethical risks that users must manage.
Ollama usage path
According to the model card, the model can be run through ollama v0.17.7 as huihui_ai/qwen3.5-abliterated:9b.
Use cases in the source record
- Image-text-to-text experimentation through the documented conversational and Ollama usage paths, with rigorous output review.
- Controlled safety-behavior research where the publisher's reduced-filtering warnings and legal responsibilities are observed.
Limitations and unknowns
- No context-window value was extracted from this record.
- No evaluation results were extracted from this record.
- Refusal-removal effectiveness is a publisher proof-of-concept claim and was not independently verified.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: huihui-ai/Huihui-Qwen3.5-9B-abliterated
Captured: Unknown. Processed: 2026-09-07T19:34:46.682965+00:00.
huihui-ai/Huihui-Qwen3.5-9B-abliterated This is an uncensored version of Qwen/Qwen3.5-9B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. ollama Please use the latest version of ollama v0.17.7 You can use huihui_ai/qwen3.5-abliterated:9b directly, ollama run huihui_ai/qwen3.5-abliterated:9b Usage Warnings Risk of Sensitive or Controversial Outputs : This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate con…
F001F002F003F004F005F006F007F009F010F011F012F013F014F015