RedTeaDev/Qwen-3.5-9b-gemini-3.1-pro-Claude-Opus-4.6-high-reasoning-v2

VISIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Mar 27, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

RedTeaDev/Qwen-3.5-9b-gemini-3.1-pro-Claude-Opus-4.6-high-reasoning-v2 is a 9 billion parameter reasoning model, fine-tuned from the Qwen3.5 architecture with a 32768 token context length. Developed by RedTeaDev, it distills Chain-Of-Thought reasoning from advanced models like Claude-4.6 Opus and Gemini-3.1 Pro to achieve a more efficient thinking pattern. This model is optimized for high-reasoning tasks, including improved Chinese instruction following, making it suitable for complex analytical queries.

Loading preview...

Overview

RedTeaDev/Qwen-3.5-9b-gemini-3.1-pro-Claude-Opus-4.6-high-reasoning-v2 is a 9 billion parameter model developed by RedTeaDev, fine-tuned from the Qwen3.5 architecture. Its primary goal is to enhance reasoning capabilities by distilling Chain-Of-Thought (CoT) patterns observed in high-performing models such as Claude-4.6 Opus and Gemini-3.1 Pro. This approach aims to refine the model's thinking process, making it more efficient and less prone to excessive reasoning for simpler queries, a common characteristic of the base Qwen3.5 family.

Key Capabilities

  • Improved Chain-Of-Thought (CoT) Reasoning: Distills advanced reasoning patterns from Claude-4.6 Opus and Gemini-3.1 Pro for more efficient problem-solving.
  • Optimized Thinking Pattern: Addresses the tendency of the base Qwen3.5 models to over-reason, leading to more concise and effective responses.
  • Enhanced Chinese Instruction Following: Incorporates the zake7749/OpenScience-Chinese-Reasoning-SFT dataset to maintain and improve performance on Chinese-language instructions.
  • Configurable Thinking: Supports an optional thinking mode, which can be enabled in GGUF formats for explicit reasoning steps.

Good For

  • Applications requiring sophisticated reasoning and analytical capabilities.
  • Tasks benefiting from distilled CoT processes for more direct answers.
  • Use cases needing strong performance in both English and Chinese instruction following, particularly for complex reasoning tasks.

Finetunes
1 models