ArchiveStudio/Qwen2.5-14B-Instruct

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 31, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

ArchiveStudio/Qwen2.5-14B-Instruct is a 14.7 billion parameter instruction-tuned causal language model developed by Qwen, part of the Qwen2.5 series. It features a 32,768 token context length, extendable to 128,000 tokens with YaRN, and supports generation up to 8,192 tokens. This model demonstrates significantly improved capabilities in coding, mathematics, instruction following, and structured data processing, making it suitable for complex analytical and generation tasks.

Loading preview...

Qwen2.5-14B-Instruct Overview

Qwen2.5-14B-Instruct is an instruction-tuned model from the Qwen2.5 series, developed by Qwen. It builds upon its predecessor, Qwen2, with substantial enhancements across several key areas. This model, featuring 14.7 billion parameters, is designed for robust performance in diverse applications.

Key Capabilities and Improvements

  • Enhanced Knowledge & Reasoning: Significantly improved capabilities in coding and mathematics, leveraging specialized expert models.
  • Instruction Following: Demonstrates stronger adherence to instructions and system prompts, beneficial for chatbots and role-play scenarios.
  • Long Text Handling: Excels at generating long texts (over 8,000 tokens) and supports an extended context length of up to 128,000 tokens using YaRN for processing extensive inputs.
  • Structured Data & Output: Improved understanding of structured data (e.g., tables) and generation of structured outputs, particularly JSON.
  • Multilingual Support: Offers broad multilingual capabilities, supporting over 29 languages including Chinese, English, French, Spanish, German, and Japanese.

When to Use This Model

Qwen2.5-14B-Instruct is particularly well-suited for use cases requiring:

  • Complex Code Generation and Analysis: Due to its enhanced coding capabilities.
  • Advanced Mathematical Problem Solving: Benefiting from specialized mathematical training.
  • Applications Requiring Strict Instruction Adherence: Such as agents or highly controlled conversational AI.
  • Processing and Generating Long Documents: Ideal for summarization, content creation, or analysis of extensive texts.
  • Structured Data Extraction and Generation: When working with tables, databases, or needing precise JSON outputs.
  • Multilingual Applications: For projects targeting a global audience across many languages.

Finetunes
1 models