MergekitCloud/mergekit-75

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 31, 2026Architecture:Transformer Featherless Exclusive Cold

MergekitCloud/mergekit-75 is an 8 billion parameter language model created by MergekitCloud, formed by merging several Llama 3.1-8B based models using the Model Stock method. It is built upon vicgalle/Humanish-Roleplay-Llama-3.1-8B as its base model. This model is specifically designed for enhanced roleplay and conversational capabilities, integrating diverse strengths from its constituent models. Its 8192 token context length supports extended and nuanced interactions.

Loading preview...

Model Overview

MergekitCloud/mergekit-75 is an 8 billion parameter language model developed by MergekitCloud, utilizing the Model Stock merge method. This model is built upon vicgalle/Humanish-Roleplay-Llama-3.1-8B as its foundational base.

Key Capabilities

This model integrates the strengths of several specialized Llama 3.1-8B variants, aiming to provide robust performance in:

  • Roleplay scenarios: Designed to handle complex and nuanced roleplaying interactions.
  • Conversational AI: Enhanced for engaging and coherent dialogue generation.
  • Creative text generation: Combines capabilities from models like Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2, Undi95/Llama3-Unholy-8B-OAS, and ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3.

Merge Details

The model was constructed using the following components:

  • Base Model: vicgalle/Humanish-Roleplay-Llama-3.1-8B
  • Merged Models:
    • Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    • Undi95/Llama3-Unholy-8B-OAS
    • ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3

This configuration leverages the Model Stock method to combine their respective strengths, resulting in a model optimized for detailed and immersive interactive applications.

Finetunes
1 models