scalejade/qwen-sea-lion-v4.5-27b-it

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 20, 2026License:mitArchitecture:Transformer Open Weights Featherless Exclusive Cold

Qwen-SEA-LION-v4.5-27B-IT is a 27-billion parameter instruction-tuned causal language model developed by AI Singapore, built upon the Qwen3.6 dense architecture. It features a hybrid Linear and Full Attention design and a large 262K context window, enabling strong reasoning capabilities. This model is specifically post-trained and optimized for multilingual and multicultural fluency across English and key Southeast Asian languages, including Burmese, Indonesian, Filipino, Malay, Tamil, Thai, and Vietnamese, making it ideal for applications requiring deep domain adaptation in the SEA region. It also supports unified vision-language tasks and agentic coding workflows.

Loading preview...

Overview

Qwen-SEA-LION-v4.5-27B-IT is a 27-billion parameter large language model developed by AI Singapore, specifically designed for the Southeast Asian (SEA) region. Built on the Qwen3.6 dense architecture, it incorporates a hybrid Linear and Full Attention design and boasts a substantial 262K context window. The model underwent distillation from Qwen3.5-397B-A17B on an updated aisingapore/SEA-Instruct-2602 dataset, enhancing its multilingual and multicultural fluency across English and seven key SEA languages: Burmese, Indonesian, Filipino, Malay, Tamil, Thai, and Vietnamese.

Key Capabilities

  • Multilingual Fluency: Optimized for English and major Southeast Asian languages.
  • Large Context Window: Features a 262K context window for advanced reasoning.
  • Reasoning & Thinking Preservation: Highly capable reasoning model with configurable thinking modes and the ability to retain historical reasoning context.
  • Agentic Coding: Designed for high-precision handling of repository-level reasoning and frontend workflows.
  • Unified Vision-Language: Early fusion training provides good performance across multimodal reasoning, coding, and visual tasks.
  • Tool Calling: Supports tool use for integrating external functionalities, demonstrated with examples for searching HDB listings and calculating mortgages.

Good For

  • Applications requiring deep linguistic and cultural understanding in Southeast Asian contexts.
  • Complex reasoning tasks that benefit from a large context window.
  • Agentic workflows and tool-augmented language generation.
  • Multimodal applications involving both text and vision.

Finetunes
1 models