magicworld7/Qwen-3.6-27B-onlyu

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 18, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The Qwen3.6-27B model by Qwen is a 27 billion parameter causal language model with a vision encoder, offering a native context length of 262,144 tokens, extensible up to 1,010,000 tokens. It is specifically optimized for agentic coding, demonstrating enhanced fluency in frontend workflows and repository-level reasoning. This model also features thinking preservation, allowing it to retain reasoning context from historical messages for streamlined iterative development.

Loading preview...

Overview

Qwen3.6-27B is a 27 billion parameter causal language model with a vision encoder, developed by Qwen. It builds upon the Qwen3.5 series, focusing on stability and real-world utility for developers. The model supports a native context length of 262,144 tokens, which can be extended up to 1,010,000 tokens using YaRN scaling techniques.

Key Capabilities

  • Agentic Coding: Significantly improved handling of frontend workflows and repository-level reasoning, making it more precise and fluent for coding tasks.
  • Thinking Preservation: Introduces a feature to retain reasoning context from past messages, enhancing decision consistency and reducing redundant reasoning in iterative development.
  • Multimodal Understanding: As a causal language model with a vision encoder, it supports both text and image inputs, and also video input, as demonstrated by its performance on various vision language benchmarks.
  • High Performance: Achieves strong results across a range of benchmarks, including coding agent tasks (e.g., SWE-bench Verified 77.2, Terminal-Bench 2.0 59.3), knowledge (MMLU-Pro 86.2), STEM & Reasoning (GPQA Diamond 87.8, AIME26 94.1), and vision language tasks (MMMU 82.9, RealWorldQA 84.1).

When to Use This Model

  • Coding and Software Development: Ideal for tasks requiring advanced agentic coding capabilities, including frontend development and repository-level code reasoning.
  • Iterative Development Workflows: Benefit from the thinking preservation feature to maintain context and streamline development processes.
  • Multimodal Applications: Suitable for applications that require understanding and generating responses based on text, images, and videos.
  • Long Context Processing: Leverage its extensive context window for complex tasks involving large amounts of information, with extensibility up to 1 million tokens.

Finetunes
1 models