DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking

VISIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Mar 17, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking is a 9 billion parameter Qwen 3.5-based language model fine-tuned by DavidAU with Claude-4.6 Opus and DECKARD datasets. It enhances reasoning and output generation, surpassing the base Qwen3.5-9B model in benchmarks, and is designed to be uncensored and highly responsive to user directives. This model supports a 32,768 token context length and is optimized for nuanced, character-driven interactions and complex reasoning tasks.

Loading preview...

Model Overview

DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking is a 9 billion parameter model based on the Qwen 3.5 architecture, fine-tuned by DavidAU. This model was trained using a unique merging process with the Claude-4.6 Opus dataset and five DECKARD datasets, specifically to refine and "trim" Qwen's reasoning capabilities, addressing hesitation and looping issues. It also integrates character and intelligence for enhanced depth.

Key Capabilities

  • Enhanced Reasoning: Training with Claude and DECKARD datasets improves the model's reasoning and output generation, outperforming the root Qwen3.5-9B model on various benchmarks.
  • Uncensored & Heretic: Designed to follow user directives without refusal, offering uncensored content generation, though it may require explicit prompting for highly graphic or explicit content.
  • Multimodal Support: Vision (image) capabilities are tested and working, with the underlying Qwen3.5 also supporting video input.
  • Optimized for Interaction: Includes recommended settings for smoother operation in chat and roleplay applications like KoboldCpp, oobabooga, and Silly Tavern.

Good For

  • Creative Content Generation: Excels in generating nuanced and character-driven narratives, especially when explicit or unconventional themes are desired.
  • Complex Reasoning Tasks: Improved reasoning capabilities make it suitable for tasks requiring deep analysis and coherent output.
  • Roleplay and Interactive Applications: Optimized settings and uncensored nature make it ideal for dynamic and unrestricted conversational AI.

Finetunes
2 models