Jaredhollins/Qwen3.8-27B-OBLITERATED

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

Jaredhollins/Qwen3.8-27B-OBLITERATED is a 27 billion parameter Qwen3.8-based causal language model, developed by Pliny the Prompter, featuring a 32768 token context length. This model is specifically engineered through "abliteration" to remove safety guardrails, providing genuinely uncensored responses without hard refusals or soft deflections. It excels in code generation and restricted queries, making it suitable for alignment research, red-teaming, and AI safety evaluation.

Loading preview...

Qwen3.8-27B-OBLITERATED: Uncensored and Liberated

This model, developed by Pliny the Prompter, is a 27 billion parameter Qwen3.8 variant specifically engineered to provide genuinely uncensored responses. Through an advanced "abliteration" process, it surgically removes safety guardrails, eliminating both hard refusals and soft deflections (safety lectures) that are common in stock models. The V3 iteration refines this process, building on iterative stacking and targeted corpus expansion to achieve liberation with a modest capability cost.

Key Capabilities & Differentiators

  • Genuinely Uncensored: Provides direct answers to restricted queries, unlike models that offer safety lectures or hard refusals.
  • High Code Generation Performance: Achieves 20/20 on tested cyber/code tasks, generating functional implementations without disclaimers.
  • Thinking ON Compatible: Works effectively with "thinking mode" enabled, offering flexibility in response generation.
  • Modest Capability Cost: While achieving full liberation, it maintains strong performance with only a -2.1pp MMLU drop compared to the stock Qwen3.8-27B.
  • Optimized Settings: Recommends specific inference parameters (temperature 0, repetition_penalty 1.15, max_new_tokens ≥ 2048) for optimal, substance-rich outputs.

Good For

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

Finetunes
1 models