sergAIAI/Qwen3.8-27B-OBLITERATED

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

sergAIAI/Qwen3.8-27B-OBLITERATED is a 27 billion parameter Qwen3.8-based language model developed by Pliny the Prompter, featuring a 32K context length. This model is uniquely engineered to be genuinely uncensored, providing direct answers and eliminating safety-lecture deflections through an iterative weight-surgery process. It excels in restricted queries and code generation tasks, making it suitable for research into refusal geometry and red-teaming scenarios.

Loading preview...

Qwen3.8-27B-OBLITERATED: Genuinely Uncensored

This model, developed by Pliny the Prompter, is a 27 billion parameter Qwen3.8 variant specifically engineered for genuine liberation from censorship. Unlike other models that merely remove hard refusals, V3 of OBLITERATED eliminates both hard refusals and soft deflections (safety lectures), providing direct and substantive answers to restricted queries.

Key Capabilities & Differentiators

  • Genuinely Uncensored: Provides real substance instead of safety lectures, even for sensitive topics.
  • High Code Generation Performance: Achieves 20/20 on cyber/code generation tasks, producing functional implementations.
  • Thinking ON Compatible: Works effectively in 'thinking mode' without refusals, offering flexibility for complex tasks.
  • Modest Capability Cost: Achieves liberation with a -2.1pp MMLU score compared to the stock model, with STEM subjects seeing the largest hit while humanities are minimally affected.
  • Advanced Refusal Removal: Utilizes an iterative weight-surgery process (abliteration) including complementary blending and targeted corpus refinement to surgically remove refusal behaviors.

Optimal Use Cases

  • 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