Gael1125/Qwen3.6-27B-V4

VISIONConcurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Qwen3.6-27B-V4 is a 27 billion parameter causal language model developed by Qwen, featuring a vision encoder and a native context length of 262,144 tokens, extensible up to 1,010,000 tokens. This model is specifically optimized for agentic coding, including frontend workflows and repository-level reasoning, and introduces thinking preservation to streamline iterative development. It demonstrates strong performance across coding, language, knowledge, STEM, and multimodal benchmarks, including vision and video understanding.

Loading preview...

What is Gael1125/Qwen3.6-27B-V4?

Gael1125/Qwen3.6-27B-V4 is a 27 billion parameter causal language model from the Qwen3.6 series, developed by Qwen. It features a vision encoder and supports a native context length of 262,144 tokens, which can be extended up to 1,010,000 tokens using YaRN scaling techniques. This model builds upon feedback from the Qwen3.5 series, focusing on enhanced stability and real-world utility, particularly for developers.

Key Differentiators

  • Agentic Coding: Significantly upgraded capabilities for handling frontend workflows and repository-level reasoning with improved fluency and precision. It excels in benchmarks like SWE-bench Verified (77.2), SWE-bench Pro (53.5), and Terminal-Bench 2.0 (59.3).
  • Thinking Preservation: Introduces an option to retain reasoning context from historical messages, which streamlines iterative development, reduces overhead, and can improve KV cache utilization.
  • Multimodal Capabilities: As a Causal Language Model with Vision Encoder, it supports both image and video inputs, demonstrating strong performance in MMMU (82.9), MathVista mini (87.4), and VideoMMMU (84.4).
  • Extended Context: Natively supports 262,144 tokens and is extensible up to 1,010,000 tokens, making it suitable for ultra-long text processing.

Should I use this for my use case?

This model is particularly well-suited for applications requiring advanced agentic coding, complex reasoning with historical context, and multimodal understanding (especially with images and videos). Its extended context window makes it ideal for tasks involving large codebases, extensive documentation, or long-form content analysis. Developers focused on building intelligent agents, code generation tools, or multimodal AI applications will find Qwen3.6-27B-V4 a strong candidate, especially given its performance in coding and reasoning benchmarks.