Darth-Coder/my-model3-14b-it

TEXT GENERATIONPricing:Input $0.48 / Output $0.96Concurrent Unit Cost:1Model Size:14BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 2, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Darth-Coder/my-model3-14b-it is a 14.8 billion parameter causal language model from the Qwen3 series, developed by Qwen. It uniquely supports seamless switching between a 'thinking mode' for complex reasoning, math, and coding, and a 'non-thinking mode' for efficient general dialogue, with a native context length of 32,768 tokens. This model excels in reasoning capabilities, human preference alignment for creative writing and role-playing, and agentic tasks, while also supporting over 100 languages.

Loading preview...

Qwen3-14B Model Overview

Qwen3-14B is a 14.8 billion parameter causal language model from the Qwen series, designed for both pretraining and post-training stages. It features a native context length of 32,768 tokens, extendable to 131,072 tokens using YaRN scaling. This model introduces a unique capability to seamlessly switch between a 'thinking mode' for complex logical reasoning, mathematics, and code generation, and a 'non-thinking mode' for efficient, general-purpose dialogue, ensuring optimal performance across diverse scenarios.

Key Capabilities

  • Adaptive Reasoning: Dynamically switches between thinking and non-thinking modes to enhance performance in complex logical reasoning, math, and coding tasks, surpassing previous Qwen models.
  • Human Preference Alignment: Excels in creative writing, role-playing, multi-turn dialogues, and instruction following, providing a more natural and engaging conversational experience.
  • Advanced Agentic Functions: Demonstrates leading performance among open-source models in complex agent-based tasks, with precise integration with external tools via frameworks like Qwen-Agent.
  • Multilingual Support: Supports over 100 languages and dialects, offering strong capabilities for multilingual instruction following and translation.
  • Long Context Handling: Natively supports 32,768 tokens, with validated performance up to 131,072 tokens using YaRN for processing extensive texts.

Good for

  • Applications requiring complex problem-solving and logical reasoning.
  • Creative content generation and interactive role-playing scenarios.
  • Agent-based systems and tool-use integration.
  • Multilingual communication and translation tasks.
  • Scenarios demanding flexible performance across both intensive reasoning and efficient general dialogue.