The abliteration process for this model, especially the thinking mode, is still being adapted. Follow this thread for updates.

This model requires Ollama 0.6.6 or later. Download Ollama

Qwen 3 is the latest generation of large language models in the Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. The flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general capabilities, etc., when compared to other top-tier models such as Qwen3-30B-A3B and Qwen3-4B.

Key Features

• Uniquely supports seamless switching between different models and configurations.
• Significantly enhances performance and efficiency through advanced algorithms.
• Superior human preference alignment for better user experience.
• Supports 100+ languages for global accessibility.

Models

• 0.6B parameter model

  ollama run jaahas/qwen3-abliterated:0.6b
  

• 1.7B parameter model

  ollama run jaahas/qwen3-abliterated:1.7b
  

• 4B parameter model

  ollama run jaahas/qwen3-abliterated:4b
  

• 8B parameter model

  ollama run jaahas/qwen3-abliterated:8b
  

• 14B parameter model

  ollama run jaahas/qwen3-abliterated:14b
  

• 32B parameter model

  coming soon
  

• 30B mixture-of-experts model with 3B active parameters

  ollama run jaahas/qwen3-abliterated:30b-a3b
  

• 235B mixture-of-experts model with 22B active parameters

  coming soon
  

Reference

• Blog