MergekitCloud/mergekit-19

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-19 is an 8 billion parameter language model created by merging several Llama 3.1-8B based models using the Model Stock method, with vicgalle/Humanish-Roleplay-Llama-3.1-8B as its base. This model is specifically optimized for roleplay and conversational tasks, integrating capabilities from models like Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 and ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3. It offers an 8192-token context length, making it suitable for extended interactive applications requiring nuanced character interactions.

Loading preview...

Model Overview

MergekitCloud/mergekit-19 is an 8 billion parameter language model developed through a merge of several Llama 3.1-8B variants. It leverages the Model Stock merging method, using vicgalle/Humanish-Roleplay-Llama-3.1-8B as its foundational base.

Key Capabilities

This model is designed to excel in interactive and character-driven applications, integrating specialized capabilities from its constituent models:

  • Enhanced Roleplay: Incorporates ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3 for advanced roleplay dynamics.
  • Flexible Content Generation: Benefits from Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 for broader content generation.
  • Open-ended Conversational Flow: Includes Undi95/Llama3-Unholy-8B-OAS to support diverse and unconstrained dialogue.

Use Cases

MergekitCloud/mergekit-19 is particularly well-suited for:

  • Creative Writing & Storytelling: Generating detailed narratives and character interactions.
  • Interactive Fiction & Games: Powering dynamic NPC dialogues and branching storylines.
  • Advanced Chatbots: Creating highly engaging and persona-driven conversational agents.

With an 8192-token context length, it can maintain coherence and context over longer interactions, making it a strong candidate for applications requiring sustained, nuanced dialogue.