MergekitCloud/mergekit-72

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-72 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 Humanish-Roleplay, Lexi-Uncensored-V2, ArliAI-RPMax-v1.3, and Unholy-8B-OAS. It is specifically optimized for advanced roleplay scenarios and uncensored conversational generation, leveraging the Model Stock merge method. With an 8192-token context length, it excels in maintaining coherent and detailed roleplay interactions.

Loading preview...

Overview

MergekitCloud/mergekit-72 is an 8 billion parameter language model, a product of the mergekit tool, designed for enhanced conversational and roleplay capabilities. It utilizes the Model Stock merge method, building upon vicgalle/Humanish-Roleplay-Llama-3.1-8B as its base.

Key Capabilities

  • Advanced Roleplay: Merges multiple Llama 3.1-8B models specifically fine-tuned for roleplay, including vicgalle/Humanish-Roleplay-Llama-3.1-8B and ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3.
  • Uncensored Generation: Incorporates models like Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 and Undi95/Llama3-Unholy-8B-OAS to provide less restricted and more open-ended responses.
  • Mergekit Integration: Created using mergekit, allowing for a blend of specialized model strengths into a single, cohesive unit.

Good For

  • Creative Writing & Storytelling: Ideal for generating detailed narratives and character interactions.
  • Roleplay Applications: Suited for scenarios requiring dynamic and nuanced role-playing.
  • Unrestricted Conversational AI: Useful for applications where broader and less filtered responses are desired.

Finetunes
1 models