MergekitCloud/mergekit-64

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-64 is an 8 billion parameter language model created by MergekitCloud, utilizing the Model Stock merge method. Built upon the Llama 3.1 architecture, it integrates several specialized Llama 3.1-8B models, including those focused on roleplay and uncensored responses. This model is primarily designed for applications requiring nuanced and unrestricted conversational capabilities, particularly in roleplaying scenarios.

Loading preview...

Overview

MergekitCloud/mergekit-64 is an 8 billion parameter language model developed by MergekitCloud. This model was created using the Model Stock merge method, a technique designed to combine the strengths of multiple pre-trained language models. Its foundation is the vicgalle/Humanish-Roleplay-Llama-3.1-8B base model, indicating an inherent focus on conversational and roleplaying applications.

Key Capabilities

  • Specialized Merged Architecture: Integrates three distinct Llama 3.1-8B models: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2, Undi95/Llama3-Unholy-8B-OAS, and ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3. This combination aims to leverage their individual strengths.
  • Roleplay Optimization: The selection of base and merged models suggests a strong optimization for generating human-like, detailed, and potentially unrestricted responses in roleplaying contexts.
  • Merge Method: Utilizes the Model Stock merge method, which is a specific technique for combining model weights.

Good For

  • Advanced Roleplaying: Ideal for scenarios requiring complex character interactions and narrative generation.
  • Uncensored Content Generation: The inclusion of "Uncensored" and "Unholy" models implies suitability for applications where content filtering is minimal or custom.
  • Conversational AI: Can be used in chatbots or interactive agents that need to maintain nuanced and extended dialogues.