kcplummer/Qwen3.8-27B-OBLITERATED

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 13, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

kcplummer/Qwen3.8-27B-OBLITERATED is a 27 billion parameter language model based on the Qwen3.8 architecture, developed by kcplummer. This model is specifically engineered for genuine uncensored responses, having undergone surgical removal of safety guardrails to eliminate both hard refusals and soft deflections. It maintains near-stock capabilities with a modest 2.1 percentage point drop in MMLU, excelling in code generation and restricted queries. It is primarily intended for alignment research, red-teaming, and AI safety evaluation requiring an unrestricted baseline.

Loading preview...

Qwen3.8-27B-OBLITERATED: Genuinely Uncensored

kcplummer/Qwen3.8-27B-OBLITERATED is a 27 billion parameter model derived from Qwen3.8, specifically engineered to provide genuinely uncensored responses. This V3 iteration, developed by kcplummer, focuses on eliminating not just hard refusals but also soft deflections and safety lectures, delivering direct answers to restricted queries.

Key Capabilities & Differentiators

  • Genuine Liberation: Provides real substance instead of safety lectures, even for sensitive prompts.
  • High Code Generation Success: Achieves 20/20 on tested code generation tasks, producing functional implementations.
  • Near-Stock Capability: Maintains strong performance with a modest -2.1 percentage point drop in MMLU compared to the stock Qwen3.8-27B.
  • Thinking ON Compatible: Works without refusals in both thinking and direct answer modes.
  • Advanced Abliteration Techniques: Utilizes iterative refinement, complementary blending, and targeted corpus surgery to remove refusal behaviors while preserving capability.
  • Optimized Settings: Recommends specific settings (temperature 0, repetition_penalty 1.15, max_new_tokens \u2265 2048, no system prompt) for optimal performance.

Ideal Use Cases

  • Alignment Research: For studying refusal geometry and safety robustness.
  • Red-Teaming: Evaluating post-training safety against weight surgery.
  • AI Safety Evaluation: As an unrestricted baseline for testing.
  • Local-First Users: For those desiring full control over model outputs on their own hardware.

Finetunes
1 models