AMAImedia/Qwen3.8-27B-Qwenseek-CyberLite-NOESIS-BF16

VISIONPricing:Input $1.6 / Cached $0.15 / Output $12Concurrent Unit Cost:2Model Size:27BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 4, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

AMAImedia/Qwen3.8-27B-Qwenseek-CyberLite-NOESIS-BF16 is a 27.8 billion parameter model based on the Qwen3.8 architecture, developed by AMAImedia as part of the NOESIS platform. This supervised fine-tune, originally by trjxter, specializes in defensive cybersecurity reasoning, secure code review, and technical problem-solving, while preserving strong coding and tool-use capabilities. It supports a 32,768 token context length and is primarily English-focused, making it suitable for cyber-related technical workflows.

Loading preview...

Model Overview

AMAImedia/Qwen3.8-27B-Qwenseek-CyberLite-NOESIS-BF16 is a 27.8 billion parameter model built on the Qwen3.8 architecture, developed by AMAImedia for its NOESIS platform. This model is a supervised fine-tune (SFT) of unsloth/Qwen3.8-27B, with its original development by trjxter. It is specifically designed to enhance defensive cybersecurity reasoning, secure code review, and evidence-driven security analysis, while carefully preserving the base model's strengths in coding, technical reasoning, and structured tool use. The model was trained using 4-bit QLoRA with BF16 compute on a mix of security, software engineering, agentic, and tool-use data, ensuring a balanced capability set.

Key Capabilities

  • Cybersecurity Specialization: Excels in defensive vulnerability analysis, secure-code review, remediation planning, and detection/containment strategies.
  • Coding and Technical Reasoning: Maintains strong performance in general coding, software engineering tasks, and complex technical problem-solving.
  • Tool Use: Preserves robust structured tool-calling behavior, crucial for agentic workflows.
  • Context Length: Validated for a context length of 32,768 tokens, allowing for extensive technical discussions and code analysis.
  • Multilingual Support: While primarily English-focused, the base Qwen architecture supports a wide range of languages.

Use Cases

This model is well-suited for:

  • Defensive cybersecurity analysis and vulnerability triage.
  • Secure software engineering and code review.
  • Remediation planning and controlled local security validation.
  • Technical reasoning and problem-solving in complex domains.
  • Code generation and review tasks.
  • Structured tool-use experiments and agentic software development.

Finetunes
1 models