huihui-ai/Huihui-OmniCoder-9B-abliterated

VISIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 31, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Huihui-OmniCoder-9B-abliterated is a 9 billion parameter language model developed by huihui-ai, derived from Tesslate/OmniCoder-9B. This model has undergone an 'abliteration' process to significantly reduce its safety filtering and refusal behaviors. It is intended for research and experimental use where the removal of safety constraints is desired, offering a less censored output compared to standard LLMs.

Loading preview...

Overview

huihui-ai/Huihui-OmniCoder-9B-abliterated is a 9 billion parameter model based on Tesslate/OmniCoder-9B, specifically modified to remove safety filtering and refusal mechanisms. This "abliteration" process aims to provide a less censored language model, allowing for a broader range of outputs that might typically be restricted by standard safety protocols.

Key Characteristics

  • Uncensored Output: Safety filtering has been significantly reduced, leading to potentially sensitive, controversial, or inappropriate content.
  • Experimental Nature: This model is a proof-of-concept for removing refusals from LLMs without using TransformerLens, as detailed in the remove-refusals-with-transformers project.
  • Ollama Integration: Directly available for use with Ollama via huihui_ai/qwen3.5-abliterated:9b-OmniCoder.

Usage Warnings

Users should be aware of the following critical points:

  • Risk of Sensitive Content: The model may generate content that is sensitive, controversial, or inappropriate.
  • Not for All Audiences: Due to limited content filtering, it is not suitable for public settings, underage users, or applications requiring high security.
  • User Responsibility: Users are solely responsible for ensuring compliance with legal and ethical standards, and for any consequences arising from generated content.
  • Recommended Use: Primarily for research, testing, or controlled environments; not recommended for direct production or public-facing commercial applications.
  • No Safety Guarantees: Unlike standard models, this model has not undergone rigorous safety optimization, and huihui.ai bears no responsibility for its use.