TADASAALOMU43/Nova-Instruct

VISIONConcurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3.6-27B is a 27 billion parameter instruction-tuned causal language model developed by Qwen, featuring a native context length of 262,144 tokens, extensible up to 1,010,000 tokens. This model is optimized for agentic coding, handling frontend workflows and repository-level reasoning with enhanced fluency and precision. It also introduces a unique 'Thinking Preservation' feature to retain reasoning context from historical messages, streamlining iterative development and improving efficiency.

Loading preview...

TADASAALOMU43/Nova-Instruct: Qwen3.6-27B

This model is the first open-weight variant of the Qwen3.6 series, a 27 billion parameter instruction-tuned causal language model developed by Qwen. It builds upon the Qwen3.5 series with substantial upgrades focused on stability and real-world utility, particularly for developers.

Key Capabilities

  • Agentic Coding: Excels in handling frontend workflows and repository-level reasoning with improved fluency and precision.
  • Thinking Preservation: Features a novel mechanism to retain reasoning context from historical messages, which streamlines iterative development and can reduce overhead.
  • Extended Context Length: Natively supports a context length of 262,144 tokens, extensible up to 1,010,000 tokens using YaRN scaling techniques.
  • Multimodal Support: Capable of processing both image and video inputs, in addition to text.
  • Performance: Demonstrates strong performance across various benchmarks, including coding agent tasks (e.g., SWE-bench Pro 53.5), knowledge (MMLU-Pro 86.2), STEM & Reasoning (AIME26 94.1), and vision language tasks (MMMU 82.9, RealWorldQA 84.1).

What Makes This Model Different?

Qwen3.6-27B distinguishes itself through its dedicated focus on agentic coding and the innovative Thinking Preservation feature. While many models offer coding capabilities, Qwen3.6-27B's enhancements for repository-level reasoning and its ability to maintain reasoning context across interactions are designed to provide a more intuitive and productive coding experience. Its robust multimodal capabilities, including video input processing, further broaden its applicability beyond typical code-centric models.

Should I Use This for My Use Case?

This model is particularly well-suited for:

  • Software Development: Developers requiring an AI assistant for complex coding tasks, especially those involving frontend development or large codebases.
  • Agent-based Applications: Building intelligent agents that benefit from persistent reasoning context and advanced tool-use capabilities.
  • Multimodal Understanding: Applications that require processing and reasoning over combined text, image, and video inputs.
  • Long-Context Tasks: Scenarios demanding very long context windows for comprehensive analysis or generation, leveraging its native 262K and extensible 1M token support.