MergekitCloud/mergekit-118

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Oct 7, 2026Architecture:Transformer Featherless Exclusive Cold

MergekitCloud/mergekit-118 is a 14.8 billion parameter language model created by MergekitCloud using the TIES merge method. It is based on Qwen/Qwen2.5-14B and incorporates Qwen/Qwen2.5-Coder-14B-Instruct, making it specialized for coding tasks. This model offers a 32768 token context length, providing extensive capacity for complex programming challenges and code generation.

Loading preview...

Overview

MergekitCloud/mergekit-118 is a 14.8 billion parameter language model, developed by MergekitCloud, that leverages the TIES (Task-Independent Equi-Sized) merge method. It is built upon the robust Qwen/Qwen2.5-14B base model and integrates the specialized capabilities of Qwen/Qwen2.5-Coder-14B-Instruct. This strategic merge aims to combine the general language understanding of the base model with enhanced coding proficiency.

Key Capabilities

  • Code-centric Performance: Inherits and enhances coding abilities from Qwen/Qwen2.5-Coder-14B-Instruct.
  • Extended Context Window: Features a 32768 token context length, suitable for handling large codebases or complex programming problems.
  • Mergekit Integration: Created using the mergekit tool, indicating a structured approach to combining model strengths.

Good For

  • Code Generation: Ideal for generating programming code across various languages.
  • Code Completion and Refactoring: Can assist developers with intelligent code suggestions and improvements.
  • Technical Problem Solving: Useful for tasks requiring an understanding of programming logic and structure.

Finetunes
1 models