Tooony133/Qwen-3.6-27B-ShadowPulse

VISIONConcurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 8, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3.6-27B is a 27 billion parameter causal language model with a vision encoder, developed by Qwen. This model prioritizes stability and real-world utility, excelling in agentic coding tasks, including frontend workflows and repository-level reasoning. It features a native context length of 262,144 tokens, extensible up to 1,010,000 tokens, and introduces a 'Thinking Preservation' option to streamline iterative development by retaining reasoning context from historical messages. The model demonstrates strong performance across various benchmarks, particularly in coding agent, knowledge, STEM, reasoning, and multimodal vision-language tasks.

Loading preview...

Qwen3.6-27B: A Robust Multimodal Model for Agentic Coding

Qwen3.6-27B is a 27 billion parameter causal language model with an integrated vision encoder, developed by Qwen. This model builds upon the Qwen3.5 series, focusing on enhanced stability and practical utility for developers.

Key Capabilities and Features

  • Agentic Coding: Significantly improved handling of frontend workflows and repository-level reasoning, making it highly proficient for development tasks.
  • Thinking Preservation: A unique feature allowing the model to retain reasoning context from historical messages, which streamlines iterative development, reduces overhead, and enhances decision consistency.
  • Multimodal Understanding: Capable of processing text, image, and video inputs, demonstrated by strong performance across various vision-language benchmarks.
  • Extended Context Length: Natively supports a context length of 262,144 tokens, with extensibility up to 1,010,000 tokens using RoPE scaling techniques like YaRN.
  • Benchmark Performance: Achieves competitive results across a wide range of benchmarks, including SWE-bench (77.2% verified), MMLU-Pro (86.2%), GPQA Diamond (87.8%), and various multimodal benchmarks like MMMU (82.9%) and V* (94.7%).

Good For

  • Software Development: Ideal for agentic coding, code generation, debugging, and repository analysis.
  • Complex Problem Solving: Excels in tasks requiring deep reasoning, such as STEM problems and mathematical competitions.
  • Multimodal Applications: Suitable for applications involving image and video understanding, visual question answering, and document analysis.
  • Iterative Development Workflows: The 'Thinking Preservation' feature makes it particularly useful for long, multi-turn interactions where maintaining context is crucial.