MergekitCloud/mergekit-67

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 28, 2026Architecture:Transformer Featherless Exclusive Cold

MergekitCloud/mergekit-67 is an 8 billion parameter language model created by MergekitCloud, built upon the Llama 3.1 architecture. This model is a merge of several specialized Llama 3.1-8B variants, including those from ArliAI, Orenguteng, and Undi95, using the Model Stock method. It is specifically designed for enhanced roleplay and creative writing applications, leveraging its merged base from vicgalle/Humanish-Roleplay-Llama-3.1-8B. With an 8192-token context length, it is optimized for generating coherent and engaging long-form interactive narratives.

Loading preview...

Overview

MergekitCloud/mergekit-67 is an 8 billion parameter language model derived from the Llama 3.1 architecture, created using the mergekit tool. This model was developed with the Model Stock merge method, utilizing vicgalle/Humanish-Roleplay-Llama-3.1-8B as its foundational base.

Key Characteristics

  • Merged Architecture: Combines the strengths of multiple specialized Llama 3.1-8B models, including:
    • ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
    • Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    • Undi95/Llama3-Unholy-8B-OAS
  • Merge Method: Employs the Model Stock technique, which is designed to integrate different model capabilities effectively.
  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports an 8192-token context window, suitable for extended interactions and detailed narrative generation.

Primary Differentiator

Unlike general-purpose LLMs, mergekit-67 is specifically engineered through its unique merge composition to excel in roleplay and creative writing scenarios. Its base model and merged components suggest a strong focus on generating human-like, engaging, and potentially unconstrained textual interactions.

Recommended Use Cases

  • Interactive Storytelling: Ideal for applications requiring dynamic and immersive narrative generation.
  • Roleplay Simulations: Suited for creating detailed character interactions and maintaining consistent personas.
  • Creative Content Generation: Can be used for generating diverse forms of creative text, from dialogues to descriptive passages.

Finetunes
1 models