MergekitCloud/mergekit-115
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-115 is a 14.8 billion parameter language model with a 32768 token context length, created by MergekitCloud using the TIES merge method. It is based on Qwen/Qwen2.5-14B and incorporates Qwen/Qwen2.5-Coder-14B-Instruct. This model is specifically optimized for coding tasks, leveraging the strengths of its constituent models to enhance performance in code generation and understanding.
Loading preview...
Overview
MergekitCloud/mergekit-115 is a 14.8 billion parameter language model, built using the TIES merge method from mergekit. It leverages Qwen/Qwen2.5-14B as its base model and integrates Qwen/Qwen2.5-Coder-14B-Instruct to enhance its capabilities.
Key Capabilities
- Code-centric Performance: Optimized for tasks requiring code generation, comprehension, and analysis, stemming from the inclusion of a dedicated coder model.
- Large Context Window: Supports a substantial context length of 32768 tokens, enabling the processing of extensive codebases or complex problem descriptions.
- Efficient Merging: Utilizes the TIES (Trimmed, Iterative, and Selective) merging technique, which selectively combines parameters from multiple models to achieve improved performance without full retraining.
Good for
- Software Development: Ideal for developers needing assistance with code completion, debugging, or generating code snippets.
- Technical Documentation: Can be used to summarize or generate technical documentation related to programming.
- Educational Tools: Suitable for applications in programming education, providing explanations or examples of code.