Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1

VISIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.3BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 9, 2026Architecture:Transformer0.0K Featherless Exclusive Cold

Josiefied-Qwen3.5-2B-gabliterated-v1 is a 2.3 billion parameter language model developed by Gökdeniz Gülmez, built upon Alibaba's Qwen3.5 architecture. This model is part of the JOSIEFIED family, which has been significantly modified to maximize uncensored behavior while maintaining strong instruction-following and tool usage capabilities. It is fine-tuned for openness and instruction alignment, making it suitable for advanced users requiring unrestricted, high-performance language generation.

Loading preview...

Model Overview

Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 is a 2.3 billion parameter model developed by Gökdeniz Gülmez, based on the Qwen3.5 architecture. It belongs to the JOSIEFIED model family, which focuses on delivering highly advanced language models with a distinct emphasis on uncensored behavior and robust instruction-following. These models are described as "gabliterated" and fine-tuned to achieve this balance, often outperforming their base counterparts on standard benchmarks.

Key Capabilities

  • Unrestricted Language Generation: Designed to maximize uncensored outputs, removing refusal vectors from its programming.
  • Strong Instruction Following: Maintains high proficiency in understanding and executing instructions.
  • Tool Usage: Capable of effective tool integration without compromise.
  • Performance: Aims to deliver raw power and utility, often exceeding base model performance.
  • Advanced Reasoning: Optimized for clear thinking, deep reasoning, and efficient problem-solving.

Intended Use Cases

This model is specifically intended for advanced users who require:

  • Unrestricted Content Generation: For applications where content filtering is not desired or needs to be bypassed.
  • High-Performance AI Assistance: When a capable and intelligent AI assistant is needed without built-in constraints.
  • Productivity-Focused Tasks: Optimized to provide helpful and accurate information efficiently.

Users should be aware that due to reduced safety filtering, the model may generate sensitive or controversial outputs and should be used responsibly.