Andronovo/Qwen3.8-27B-OBLITERATED

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 26, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Andronovo/Qwen3.8-27B-OBLITERATED is a 27 billion parameter Qwen3.8-based causal language model developed by Andronovo, featuring a 32768 token context length. This model is uniquely engineered to be genuinely uncensored, providing direct answers and eliminating safety-lecture deflections through an iterative 'abliteration' process. It excels at code generation and restricted queries, making it suitable for research into refusal geometry and red-teaming scenarios.

Loading preview...

Model Overview: Qwen3.8-27B-OBLITERATED

Andronovo/Qwen3.8-27B-OBLITERATED is a 27 billion parameter model based on the Qwen3.8 architecture, distinguished by its "abliteration" process that surgically removes safety guardrails. This V3 iteration focuses on providing genuinely uncensored responses, eliminating both hard refusals and soft deflections (safety lectures) that are common in stock LLMs. It maintains near-stock capability with a modest MMLU drop of 2.1 percentage points, primarily affecting STEM tasks.

Key Capabilities & Differentiators

  • Genuine Liberation: Provides direct answers to restricted queries, including those related to security research and red-team scenarios, without safety lectures.
  • Exceptional Code Generation: Achieves 20/20 on tested cyber/code tasks, generating functional implementations.
  • Thinking ON Compatible: Works effectively with or without a 'thinking' mode, offering flexibility in response generation.
  • Optimized Settings: Recommends specific inference parameters (temperature 0, repetition_penalty 1.15, max_new_tokens ≥ 2048) for optimal, complete, and code-rich outputs.
  • Advanced Abliteration Technique: Utilizes iterative refinement, complementary blending of SVD and LEACE methods, and targeted corpus surgery to achieve its uncensored nature.

Ideal Use Cases

  • Alignment Research: For studying refusal geometry and evaluating safety robustness in LLMs.
  • Red-Teaming: To assess post-training safety mechanisms against weight surgery.
  • AI Safety Evaluation: As an unrestricted baseline for comprehensive safety assessments.
  • Local-First Users: For those requiring full control over model outputs on their own hardware.

Finetunes
1 models