MergekitCloud/mergekit-66

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-66 is an 8 billion parameter language model created by merging several Llama 3.1-8B based models using the Model Stock method. It leverages vicgalle/Humanish-Roleplay-Llama-3.1-8B as its base, integrating capabilities from Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2, Undi95/Llama3-Unholy-8B-OAS, and ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3. This merge aims to combine and enhance the roleplay and conversational strengths of its constituent models, making it suitable for nuanced interactive applications.

Loading preview...

Model Overview

MergekitCloud/mergekit-66 is an 8 billion parameter language model developed through a merge of several pre-trained Llama 3.1-8B variants. This model was constructed using the Model Stock merge method, a technique designed to combine the strengths of multiple base models.

Merge Details

The merging process utilized vicgalle/Humanish-Roleplay-Llama-3.1-8B as the foundational base model. The following models were integrated to create mergekit-66:

This configuration suggests an emphasis on combining diverse conversational and roleplay capabilities from its constituent models, potentially offering a broader range of stylistic outputs and improved interactive performance.

Key Characteristics

  • Architecture: Based on the Llama 3.1-8B family.
  • Merge Method: Employs the Model Stock method for integration.
  • Parameter Count: 8 billion parameters.
  • Context Length: Supports an 8192 token context window.

Potential Use Cases

Given its origins from roleplay-focused base models, mergekit-66 is likely well-suited for applications requiring:

  • Advanced Roleplay Scenarios: Generating detailed and consistent character interactions.
  • Creative Writing: Assisting with narrative generation and dialogue.
  • Interactive Storytelling: Powering dynamic and responsive conversational agents.