droplychee/droplychee-1.0-27b
VISIONConcurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 17, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold
Droplychee-1.0-27B is a multilingual decoder-only large language model developed by Droplychee AI Research, built upon Qwen/Qwen3.6-27B. This instruction-tuned model supports long-context inference up to 1,000,000 tokens and excels in multilingual understanding across English, Bangla, and 40+ other languages. It is optimized for instruction following, reasoning, and software development, making it suitable for AI agents and long document processing.
Loading preview...
Droplychee-1.0-27B: Open Multilingual LLM
Droplychee-1.0-27B, developed by Droplychee AI Research, is a multilingual decoder-only large language model built on Qwen/Qwen3.6-27B. It has been refined through full supervised fine-tuning and model merging to enhance its capabilities across various domains.
Key Capabilities
- Exceptional Long Context: Supports inference up to 1,000,000 tokens, enabling deep analysis of extensive documents and complex information.
- Multilingual Proficiency: Designed for English, Bangla, and over 40 other languages, facilitating global applications and translation tasks.
- Instruction Following & Reasoning: Optimized for precise instruction adherence, logical problem-solving, and general question answering.
- Coding & Software Development: Excels in coding assistance, software engineering, and technical documentation generation.
- AI Agent Ready: Built to support AI agent workflows, making it suitable for automation and intelligent system integration.
Good For
- Long Document Processing: Ideal for summarizing, analyzing, and retrieving information from very long texts.
- Multilingual AI Applications: Suitable for translation, cross-lingual understanding, and content generation in diverse languages.
- Software Development: Assists with code generation, debugging, and technical writing.
- AI Agents & Research: Powers intelligent agents and supports complex research assistance tasks.