emogie3D/Mistral-Nemo-Base-2407-RP-Merge

TEXT GENERATIONConcurrent Unit Cost:1Model Size:12BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Sep 9, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

emogie3D/Mistral-Nemo-Base-2407-RP-Merge is a 12 billion parameter language model with a 32768-token context length, created by emogie3D through a merge of eight specialized models using the Model Stock method. This model is specifically optimized for uncensored role-playing and fictional entertainment purposes. It integrates components from models like Astra-v1, Chronos-Gold, dolphin-2.9.3, Muse, Pantheon-RP, Pygmalion-3, Wayfarer-2, and Zinakha to enhance its capabilities in generating creative and unconstrained narrative content.

Loading preview...

Model Overview

emogie3D/Mistral-Nemo-Base-2407-RP-Merge is a 12 billion parameter language model designed with a 32768-token context window. It was developed by emogie3D using the Model Stock merge method, combining eight distinct pre-trained language models. The primary focus of this merge was to create a model highly capable of uncensored role-playing and generating content for fictional and entertainment use cases.

Key Characteristics

  • Specialized Merge: Utilizes the Model Stock method, building upon Chronos-Gold-12B-1.0 as its base model.
  • Composite Architecture: Integrates capabilities from a diverse set of models including P0x0/Astra-v1-12B, elinas/Chronos-Gold-12B-1.0, dphn/dolphin-2.9.3-mistral-nemo-12b, LatitudeGames/Muse-12B, Gryphe/Pantheon-RP-1.6-12b-Nemo, PygmalionAI/Pygmalion-3-12B, LatitudeGames/Wayfarer-2-12B, and aixonlab/Zinakha-12b.
  • Role-Playing Optimization: Explicitly engineered for generating dynamic and unconstrained narratives, making it suitable for interactive storytelling and character-driven scenarios.

Use Case

This model is specifically intended for:

  • Fictional and Entertainment Purposes: Generating creative stories, dialogues, and scenarios.
  • Uncensored Role-Playing: Providing responses that are not constrained by typical content filters, allowing for a broader range of narrative possibilities.

Users should note that any usage outside of fictional and entertainment contexts is considered out of scope for this model.

Finetunes
3 models