MergekitCloud/mergekit-73

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 29, 2026Architecture:Transformer Featherless Exclusive Cold

MergekitCloud/mergekit-73 is an 8 billion parameter language model with an 8192 token context length, created by merging several Llama 3.1-8B based models using the Model Stock method. This model is specifically designed for enhanced roleplay capabilities, building upon a Humanish-Roleplay-Llama-3.1-8B base. It integrates specialized models to offer a robust foundation for interactive and nuanced conversational applications.

Loading preview...

Overview

MergekitCloud/mergekit-73 is an 8 billion parameter language model with an 8192 token context length, developed through a merge of pre-trained models using the mergekit tool. It utilizes the Model Stock merge method, with vicgalle/Humanish-Roleplay-Llama-3.1-8B serving as its foundational base model.

Key Capabilities

This model is specifically engineered by combining several Llama 3.1-8B variants, focusing on advanced roleplay scenarios. The merged components include:

  • ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
  • Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
  • Undi95/Llama3-Unholy-8B-OAS

This combination aims to provide a versatile and nuanced model for generating human-like, engaging, and detailed roleplay interactions.

Ideal Use Cases

  • Roleplay Applications: Excels in generating dynamic and contextually rich responses for various roleplay scenarios.
  • Interactive Storytelling: Suitable for applications requiring models to maintain character consistency and narrative flow.
  • Conversational AI: Can be leveraged for chatbots or virtual assistants where detailed and imaginative dialogue is crucial.

Finetunes
1 models