Ddraco42/Qwen3.8-27B-OBLITERATED

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 17, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Ddraco42/Qwen3.8-27B-OBLITERATED is a 27 billion parameter language model based on the Qwen3.8 architecture, developed by Ddraco42. This model is specifically engineered for genuine uncensored responses, having undergone "abliteration" to remove both hard refusals and soft deflections, providing direct answers without safety lectures. It maintains near-stock capabilities with a modest MMLU drop of 2.1 percentage points, excelling in code generation and restricted queries, making it suitable for research into refusal geometry and red-teaming scenarios.

Loading preview...

Qwen3.8-27B — OBLITERATED: Genuinely Uncensored

Ddraco42/Qwen3.8-27B-OBLITERATED is a 27 billion parameter language model derived from the Qwen3.8 base, specifically engineered for genuine uncensored responses. This model has undergone a unique "abliteration" process (V3) to eliminate not only hard refusals but also soft deflections and safety lectures, providing direct and substantive answers to restricted queries. It achieves this while maintaining near-stock capabilities, with a modest MMLU drop of 2.1 percentage points.

Key Capabilities

  • Genuinely Uncensored: Provides real answers to restricted queries, eliminating safety lectures and hard refusals.
  • High Code Generation Performance: Achieves 20/20 on tested code generation tasks, producing functional implementations.
  • Thinking ON Compatible: Works effectively with or without "thinking mode" enabled, offering flexibility in response generation.
  • Modest Capability Cost: Maintains strong performance with only a -2.1pp MMLU score reduction compared to the stock model.
  • Advanced Real-World Tasks: Performs well on complex tasks like ReAct agent loops, async code refactoring, and security code review.

Good For

  • Alignment Researchers: Ideal for studying refusal geometry and safety robustness in LLMs.
  • Red-Teamers: Useful for evaluating post-training safety mechanisms against weight surgery.
  • AI Safety Evaluators: Provides an unrestricted baseline for comprehensive safety assessments.
  • Local-First Users: Offers full control over model outputs for those running models on their own hardware.

Finetunes
1 models