ArRENCEAI/Qwen2.5-3B-Instruct-OBLITERATED

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 9, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

ArRENCEAI/Qwen2.5-3B-Instruct-OBLITERATED is a 3.1 billion parameter instruction-tuned causal language model based on Qwen/Qwen2.5-3B-Instruct. Developed by ArRENCE AI, this model has been processed using the 'advanced' method via OBLITERATUS to remove refusal behavior. It is designed for research and entertainment purposes, offering unrestricted content generation.

Loading preview...

Overview

ArRENCEAI/Qwen2.5-3B-Instruct-OBLITERATED is a 3.1 billion parameter instruction-tuned language model derived from the Qwen/Qwen2.5-3B-Instruct base model. It has undergone a process called "abliteration" using the advanced method of the OBLITERATUS tool. This modification aims to remove refusal behavior from the model, allowing it to generate unrestricted content.

Key Characteristics

  • Base Model: Qwen/Qwen2.5-3B-Instruct
  • Parameter Count: 3.1 billion
  • Context Length: 32768 tokens
  • Modification Method: advanced abliteration via OBLITERATUS
  • Content Generation: Designed to be uncensored and generate unrestricted content.

Intended Use

This model is provided by ArRENCE AI primarily for research and entertainment purposes. Users should be aware that due to its uncensored nature, it may produce content that is offensive, inaccurate, harmful, or otherwise inappropriate. Users are solely responsible for ensuring their use complies with all applicable laws and regulations, and use is entirely at their own risk.

Finetunes
1 models